Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2083 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3175. Min Range: -6.3175
Max Act: 6.3175. Min Act: -0.1700
Data Index: 7466881 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3175. Min Range: -6.3175
Max Act: 6.1925. Min Act: -0.1700
Data Index: 7000488 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3175. Min Range: -6.3175
Max Act: 6.0987. Min Act: -0.1700
Data Index: 7531559 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3175. Min Range: -6.3175
Max Act: 5.8487. Min Act: -0.1700
Data Index: 8817069 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3175. Min Range: -6.3175
Max Act: 5.7862. Min Act: -0.1700
Data Index: 322488 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3175. Min Range: -6.3175
Max Act: 5.8175. Min Act: -0.1700
Data Index: 4176675 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3175. Min Range: -6.3175
Max Act: 5.7862. Min Act: -0.1700
Data Index: 8013995 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3175. Min Range: -6.3175
Max Act: 5.7550. Min Act: -0.1700
Data Index: 8084796 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3175. Min Range: -6.3175
Max Act: 5.7550. Min Act: -0.1700
Data Index: 2651606 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3175. Min Range: -6.3175
Max Act: 5.6925. Min Act: -0.1700
Data Index: 6042005 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3175. Min Range: -6.3175
Max Act: 5.6925. Min Act: -0.1700
Data Index: 7115409 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3175. Min Range: -6.3175
Max Act: 5.6925. Min Act: -0.1700
Data Index: 3568289 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3175. Min Range: -6.3175
Max Act: 5.6612. Min Act: -0.1700
Data Index: 4714101 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3175. Min Range: -6.3175
Max Act: 5.6300. Min Act: -0.1700
Data Index: 812456 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3175. Min Range: -6.3175
Max Act: 5.6300. Min Act: -0.1700
Data Index: 1843138 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3175. Min Range: -6.3175
Max Act: 5.6300. Min Act: -0.1700
Data Index: 4262131 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3175. Min Range: -6.3175
Max Act: 5.5987. Min Act: -0.1700
Data Index: 2342034 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3175. Min Range: -6.3175
Max Act: 5.5987. Min Act: -0.1700
Data Index: 7778267 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3175. Min Range: -6.3175
Max Act: 5.5675. Min Act: -0.1700
Data Index: 2179292 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3175. Min Range: -6.3175
Max Act: 5.5675. Min Act: -0.1700
Data Index: 1402750 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #19