Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3876 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3098. Min Range: -6.3098
Max Act: 6.3098. Min Act: -0.1700
Data Index: 5254019 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3098. Min Range: -6.3098
Max Act: 6.2473. Min Act: -0.1700
Data Index: 2847598 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3098. Min Range: -6.3098
Max Act: 6.2161. Min Act: -0.1700
Data Index: 4251594 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3098. Min Range: -6.3098
Max Act: 6.1223. Min Act: -0.1700
Data Index: 3814441 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3098. Min Range: -6.3098
Max Act: 6.1536. Min Act: -0.1700
Data Index: 3919897 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3098. Min Range: -6.3098
Max Act: 6.1536. Min Act: -0.1700
Data Index: 2868114 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3098. Min Range: -6.3098
Max Act: 6.1223. Min Act: -0.1700
Data Index: 3269958 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3098. Min Range: -6.3098
Max Act: 6.1223. Min Act: -0.1700
Data Index: 3427967 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3098. Min Range: -6.3098
Max Act: 6.0598. Min Act: -0.1700
Data Index: 281924 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3098. Min Range: -6.3098
Max Act: 6.1223. Min Act: -0.1700
Data Index: 6436995 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3098. Min Range: -6.3098
Max Act: 6.0598. Min Act: -0.1700
Data Index: 5546547 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3098. Min Range: -6.3098
Max Act: 6.0911. Min Act: -0.1700
Data Index: 7305771 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3098. Min Range: -6.3098
Max Act: 6.0286. Min Act: -0.1700
Data Index: 8017171 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3098. Min Range: -6.3098
Max Act: 6.0286. Min Act: -0.1700
Data Index: 6822097 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3098. Min Range: -6.3098
Max Act: 5.9973. Min Act: -0.1700
Data Index: 8566986 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3098. Min Range: -6.3098
Max Act: 5.9973. Min Act: -0.1700
Data Index: 2054317 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3098. Min Range: -6.3098
Max Act: 5.9661. Min Act: -0.1700
Data Index: 5814098 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3098. Min Range: -6.3098
Max Act: 5.9348. Min Act: -0.1700
Data Index: 6666166 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3098. Min Range: -6.3098
Max Act: 5.9661. Min Act: -0.1700
Data Index: 8790704 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3098. Min Range: -6.3098
Max Act: 5.9036. Min Act: -0.1700
Data Index: 2518980 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19