Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 26 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8214. Min Range: -5.8214
Max Act: 5.8214. Min Act: -0.1700
Data Index: 6526702 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8214. Min Range: -5.8214
Max Act: 5.6339. Min Act: -0.1700
Data Index: 7755953 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8214. Min Range: -5.8214
Max Act: 5.6027. Min Act: -0.1700
Data Index: 1384882 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8214. Min Range: -5.8214
Max Act: 5.6027. Min Act: -0.1700
Data Index: 7992887 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8214. Min Range: -5.8214
Max Act: 5.5714. Min Act: -0.1700
Data Index: 7174034 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8214. Min Range: -5.8214
Max Act: 5.5714. Min Act: -0.1700
Data Index: 6653296 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8214. Min Range: -5.8214
Max Act: 5.5089. Min Act: -0.1700
Data Index: 5279489 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8214. Min Range: -5.8214
Max Act: 5.5089. Min Act: -0.1700
Data Index: 5532894 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8214. Min Range: -5.8214
Max Act: 5.5089. Min Act: -0.1700
Data Index: 5195499 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8214. Min Range: -5.8214
Max Act: 5.4777. Min Act: -0.1700
Data Index: 3271525 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8214. Min Range: -5.8214
Max Act: 5.4777. Min Act: -0.1700
Data Index: 799409 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8214. Min Range: -5.8214
Max Act: 5.4777. Min Act: -0.1700
Data Index: 5216175 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8214. Min Range: -5.8214
Max Act: 5.5089. Min Act: -0.1700
Data Index: 8629551 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8214. Min Range: -5.8214
Max Act: 5.4464. Min Act: -0.1700
Data Index: 1254872 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8214. Min Range: -5.8214
Max Act: 5.4464. Min Act: -0.1700
Data Index: 3191776 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8214. Min Range: -5.8214
Max Act: 5.4464. Min Act: -0.1700
Data Index: 6460702 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8214. Min Range: -5.8214
Max Act: 5.4464. Min Act: -0.1700
Data Index: 7857023 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8214. Min Range: -5.8214
Max Act: 5.4464. Min Act: -0.1700
Data Index: 8666127 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8214. Min Range: -5.8214
Max Act: 5.4777. Min Act: -0.1700
Data Index: 7768100 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8214. Min Range: -5.8214
Max Act: 5.4152. Min Act: -0.1700
Data Index: 1596038 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #19