Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 855 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0549. Min Range: -6.0549
Max Act: 6.0549. Min Act: -0.1700
Data Index: 7368164 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0549. Min Range: -6.0549
Max Act: 5.7111. Min Act: -0.1700
Data Index: 7368163 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0549. Min Range: -6.0549
Max Act: 5.6799. Min Act: -0.1700
Data Index: 6381121 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0549. Min Range: -6.0549
Max Act: 5.6486. Min Act: -0.1700
Data Index: 4614451 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0549. Min Range: -6.0549
Max Act: 5.5861. Min Act: -0.1700
Data Index: 3061703 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0549. Min Range: -6.0549
Max Act: 5.6174. Min Act: -0.1700
Data Index: 2639414 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0549. Min Range: -6.0549
Max Act: 5.5549. Min Act: -0.1700
Data Index: 2867394 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0549. Min Range: -6.0549
Max Act: 5.5236. Min Act: -0.1700
Data Index: 4508819 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0549. Min Range: -6.0549
Max Act: 5.4924. Min Act: -0.1700
Data Index: 1974689 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0549. Min Range: -6.0549
Max Act: 5.4924. Min Act: -0.1700
Data Index: 3590126 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0549. Min Range: -6.0549
Max Act: 5.5236. Min Act: -0.1700
Data Index: 4985879 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0549. Min Range: -6.0549
Max Act: 5.4611. Min Act: -0.1700
Data Index: 7313302 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0549. Min Range: -6.0549
Max Act: 5.4611. Min Act: -0.1700
Data Index: 4032637 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0549. Min Range: -6.0549
Max Act: 5.4611. Min Act: -0.1700
Data Index: 5915589 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0549. Min Range: -6.0549
Max Act: 5.4611. Min Act: -0.1700
Data Index: 8239115 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0549. Min Range: -6.0549
Max Act: 5.4611. Min Act: -0.1700
Data Index: 767020 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0549. Min Range: -6.0549
Max Act: 5.3986. Min Act: -0.1700
Data Index: 3887840 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0549. Min Range: -6.0549
Max Act: 5.4299. Min Act: -0.1700
Data Index: 1721700 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0549. Min Range: -6.0549
Max Act: 5.4299. Min Act: -0.1700
Data Index: 1436419 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0549. Min Range: -6.0549
Max Act: 5.3986. Min Act: -0.1700
Data Index: 4866374 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #19