Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1434 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4166. Min Range: -6.4166
Max Act: 6.4166. Min Act: -0.1700
Data Index: 5829225 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4166. Min Range: -6.4166
Max Act: 6.3541. Min Act: -0.1700
Data Index: 3284772 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4166. Min Range: -6.4166
Max Act: 6.3541. Min Act: -0.1700
Data Index: 401967 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4166. Min Range: -6.4166
Max Act: 6.3229. Min Act: -0.1700
Data Index: 3675229 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4166. Min Range: -6.4166
Max Act: 6.2291. Min Act: -0.1700
Data Index: 26440 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4166. Min Range: -6.4166
Max Act: 6.1979. Min Act: -0.1700
Data Index: 5341075 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4166. Min Range: -6.4166
Max Act: 6.1666. Min Act: -0.1700
Data Index: 3549863 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4166. Min Range: -6.4166
Max Act: 6.1354. Min Act: -0.1700
Data Index: 1171477 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4166. Min Range: -6.4166
Max Act: 6.0729. Min Act: -0.1700
Data Index: 7815802 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4166. Min Range: -6.4166
Max Act: 6.0729. Min Act: -0.1700
Data Index: 2236550 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4166. Min Range: -6.4166
Max Act: 6.0729. Min Act: -0.1700
Data Index: 1670413 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4166. Min Range: -6.4166
Max Act: 6.0729. Min Act: -0.1700
Data Index: 6715391 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4166. Min Range: -6.4166
Max Act: 6.0416. Min Act: -0.1700
Data Index: 3918233 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4166. Min Range: -6.4166
Max Act: 6.0104. Min Act: -0.1700
Data Index: 3444138 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4166. Min Range: -6.4166
Max Act: 5.9791. Min Act: -0.1700
Data Index: 5257904 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4166. Min Range: -6.4166
Max Act: 5.9479. Min Act: -0.1700
Data Index: 3946575 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4166. Min Range: -6.4166
Max Act: 5.9479. Min Act: -0.1700
Data Index: 5949369 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4166. Min Range: -6.4166
Max Act: 5.9166. Min Act: -0.1700
Data Index: 2987653 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4166. Min Range: -6.4166
Max Act: 5.9479. Min Act: -0.1700
Data Index: 407548 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4166. Min Range: -6.4166
Max Act: 5.8541. Min Act: -0.1700
Data Index: 5802880 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19