Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4956 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4379. Min Range: -5.4379
Max Act: 5.4379. Min Act: -0.1700
Data Index: 3043699 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4379. Min Range: -5.4379
Max Act: 5.3754. Min Act: -0.1700
Data Index: 781764 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4379. Min Range: -5.4379
Max Act: 5.3754. Min Act: -0.1700
Data Index: 810874 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4379. Min Range: -5.4379
Max Act: 5.3441. Min Act: -0.1700
Data Index: 1777813 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4379. Min Range: -5.4379
Max Act: 5.2504. Min Act: -0.1700
Data Index: 1337311 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4379. Min Range: -5.4379
Max Act: 5.2504. Min Act: -0.1700
Data Index: 66585 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4379. Min Range: -5.4379
Max Act: 5.2191. Min Act: -0.1700
Data Index: 2582378 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4379. Min Range: -5.4379
Max Act: 5.1254. Min Act: -0.1700
Data Index: 8376635 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4379. Min Range: -5.4379
Max Act: 5.1254. Min Act: -0.1700
Data Index: 6219848 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4379. Min Range: -5.4379
Max Act: 5.0629. Min Act: -0.1700
Data Index: 556654 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4379. Min Range: -5.4379
Max Act: 5.0629. Min Act: -0.1700
Data Index: 5012107 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4379. Min Range: -5.4379
Max Act: 5.0316. Min Act: -0.1700
Data Index: 1403158 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4379. Min Range: -5.4379
Max Act: 5.0316. Min Act: -0.1700
Data Index: 4680110 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4379. Min Range: -5.4379
Max Act: 5.0316. Min Act: -0.1700
Data Index: 6967063 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4379. Min Range: -5.4379
Max Act: 5.0004. Min Act: -0.1700
Data Index: 5780269 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4379. Min Range: -5.4379
Max Act: 4.9691. Min Act: -0.1700
Data Index: 4602892 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4379. Min Range: -5.4379
Max Act: 4.9691. Min Act: -0.1700
Data Index: 1084687 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4379. Min Range: -5.4379
Max Act: 4.9691. Min Act: -0.1700
Data Index: 5834448 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4379. Min Range: -5.4379
Max Act: 4.9379. Min Act: -0.1700
Data Index: 7038168 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4379. Min Range: -5.4379
Max Act: 4.9379. Min Act: -0.1700
Data Index: 31003 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #19