Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4536 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7526. Min Range: -5.7526
Max Act: 5.7526. Min Act: -0.1700
Data Index: 2239034 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7526. Min Range: -5.7526
Max Act: 5.5026. Min Act: -0.1700
Data Index: 5833126 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7526. Min Range: -5.7526
Max Act: 5.4713. Min Act: -0.1700
Data Index: 2635372 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7526. Min Range: -5.7526
Max Act: 5.4401. Min Act: -0.1700
Data Index: 3156312 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7526. Min Range: -5.7526
Max Act: 5.4401. Min Act: -0.1700
Data Index: 1334888 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7526. Min Range: -5.7526
Max Act: 5.4088. Min Act: -0.1700
Data Index: 3312500 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7526. Min Range: -5.7526
Max Act: 5.3151. Min Act: -0.1700
Data Index: 8041226 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7526. Min Range: -5.7526
Max Act: 5.2526. Min Act: -0.1700
Data Index: 936362 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7526. Min Range: -5.7526
Max Act: 5.2526. Min Act: -0.1700
Data Index: 7527116 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7526. Min Range: -5.7526
Max Act: 5.2838. Min Act: -0.1700
Data Index: 3218280 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7526. Min Range: -5.7526
Max Act: 5.2526. Min Act: -0.1700
Data Index: 8686905 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7526. Min Range: -5.7526
Max Act: 5.2526. Min Act: -0.1700
Data Index: 8748115 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7526. Min Range: -5.7526
Max Act: 5.2213. Min Act: -0.1700
Data Index: 824302 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7526. Min Range: -5.7526
Max Act: 5.1901. Min Act: -0.1700
Data Index: 3312517 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7526. Min Range: -5.7526
Max Act: 5.1901. Min Act: -0.1700
Data Index: 3312498 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7526. Min Range: -5.7526
Max Act: 5.1901. Min Act: -0.1700
Data Index: 7377012 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7526. Min Range: -5.7526
Max Act: 5.1901. Min Act: -0.1700
Data Index: 932945 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7526. Min Range: -5.7526
Max Act: 5.1588. Min Act: -0.1700
Data Index: 5459157 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7526. Min Range: -5.7526
Max Act: 5.1276. Min Act: -0.1700
Data Index: 5308524 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7526. Min Range: -5.7526
Max Act: 5.1588. Min Act: -0.1700
Data Index: 6114164 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #19