Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3953 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.8855. Min Act: -0.1700
Data Index: 6277173 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.5105. Min Act: -0.1700
Data Index: 4687904 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.4167. Min Act: -0.1700
Data Index: 5283367 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.2917. Min Act: -0.1700
Data Index: 779568 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.2917. Min Act: -0.1700
Data Index: 7781116 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.2605. Min Act: -0.1700
Data Index: 571432 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.1980. Min Act: -0.1700
Data Index: 7995688 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.1980. Min Act: -0.1700
Data Index: 7427321 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.1355. Min Act: -0.1700
Data Index: 8522214 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.1355. Min Act: -0.1700
Data Index: 8230754 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.1355. Min Act: -0.1700
Data Index: 2548536 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.1355. Min Act: -0.1700
Data Index: 1380614 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.1355. Min Act: -0.1700
Data Index: 6509626 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.1667. Min Act: -0.1700
Data Index: 5342772 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.1355. Min Act: -0.1700
Data Index: 4518536 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.1042. Min Act: -0.1700
Data Index: 1758217 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.1042. Min Act: -0.1700
Data Index: 953519 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.1042. Min Act: -0.1700
Data Index: 7664749 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.1042. Min Act: -0.1700
Data Index: 6886257 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.0730. Min Act: -0.1700
Data Index: 7302555 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19