Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5637 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6111. Min Range: -5.6111
Max Act: 5.6111. Min Act: -0.1700
Data Index: 8514846 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6111. Min Range: -5.6111
Max Act: 5.6111. Min Act: -0.1700
Data Index: 7713437 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6111. Min Range: -5.6111
Max Act: 5.5799. Min Act: -0.1700
Data Index: 861586 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6111. Min Range: -5.6111
Max Act: 5.5486. Min Act: -0.1700
Data Index: 8632470 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6111. Min Range: -5.6111
Max Act: 5.5486. Min Act: -0.1700
Data Index: 8720247 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6111. Min Range: -5.6111
Max Act: 5.5486. Min Act: -0.1700
Data Index: 5865502 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6111. Min Range: -5.6111
Max Act: 5.5486. Min Act: -0.1700
Data Index: 4292292 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6111. Min Range: -5.6111
Max Act: 5.5486. Min Act: -0.1700
Data Index: 233967 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6111. Min Range: -5.6111
Max Act: 5.4861. Min Act: -0.1700
Data Index: 885531 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6111. Min Range: -5.6111
Max Act: 5.5174. Min Act: -0.1700
Data Index: 3248142 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6111. Min Range: -5.6111
Max Act: 5.5174. Min Act: -0.1700
Data Index: 7354770 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6111. Min Range: -5.6111
Max Act: 5.5174. Min Act: -0.1700
Data Index: 42371 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6111. Min Range: -5.6111
Max Act: 5.4861. Min Act: -0.1700
Data Index: 5483837 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6111. Min Range: -5.6111
Max Act: 5.4549. Min Act: -0.1700
Data Index: 2456572 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6111. Min Range: -5.6111
Max Act: 5.4861. Min Act: -0.1700
Data Index: 7213906 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6111. Min Range: -5.6111
Max Act: 5.4549. Min Act: -0.1700
Data Index: 4716486 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6111. Min Range: -5.6111
Max Act: 5.4549. Min Act: -0.1700
Data Index: 4416260 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6111. Min Range: -5.6111
Max Act: 5.4236. Min Act: -0.1700
Data Index: 3384830 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6111. Min Range: -5.6111
Max Act: 5.4549. Min Act: -0.1700
Data Index: 7433341 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6111. Min Range: -5.6111
Max Act: 5.4549. Min Act: -0.1700
Data Index: 3441248 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19