Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3583 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 11.8544. Min Range: -11.8544
Max Act: 11.8544. Min Act: -0.1700
Data Index: 8043185 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.8544. Min Range: -11.8544
Max Act: 11.6669. Min Act: -0.1700
Data Index: 8558558 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.8544. Min Range: -11.8544
Max Act: 11.6669. Min Act: -0.1700
Data Index: 5566766 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.8544. Min Range: -11.8544
Max Act: 11.5419. Min Act: -0.1700
Data Index: 2041247 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.8544. Min Range: -11.8544
Max Act: 11.4794. Min Act: -0.1700
Data Index: 3109270 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.8544. Min Range: -11.8544
Max Act: 11.4794. Min Act: -0.1700
Data Index: 5871885 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.8544. Min Range: -11.8544
Max Act: 11.4169. Min Act: -0.1700
Data Index: 5094706 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.8544. Min Range: -11.8544
Max Act: 11.3544. Min Act: -0.1700
Data Index: 7045402 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.8544. Min Range: -11.8544
Max Act: 11.3544. Min Act: -0.1700
Data Index: 5140328 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.8544. Min Range: -11.8544
Max Act: 11.2919. Min Act: -0.1700
Data Index: 3497991 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.8544. Min Range: -11.8544
Max Act: 11.2919. Min Act: -0.1700
Data Index: 4989220 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.8544. Min Range: -11.8544
Max Act: 11.2919. Min Act: -0.1700
Data Index: 8418100 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.8544. Min Range: -11.8544
Max Act: 11.2294. Min Act: -0.1700
Data Index: 8207970 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.8544. Min Range: -11.8544
Max Act: 11.2294. Min Act: -0.1700
Data Index: 5881496 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.8544. Min Range: -11.8544
Max Act: 11.2294. Min Act: -0.1700
Data Index: 515877 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.8544. Min Range: -11.8544
Max Act: 11.1669. Min Act: -0.1700
Data Index: 865682 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.8544. Min Range: -11.8544
Max Act: 11.1669. Min Act: -0.1700
Data Index: 5303662 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.8544. Min Range: -11.8544
Max Act: 11.1044. Min Act: -0.1700
Data Index: 5842120 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.8544. Min Range: -11.8544
Max Act: 11.1669. Min Act: -0.1700
Data Index: 7227904 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.8544. Min Range: -11.8544
Max Act: 11.1669. Min Act: -0.1700
Data Index: 830891 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19