Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 612 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5568. Min Range: -6.5568
Max Act: 6.5568. Min Act: -0.1700
Data Index: 2018864 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5568. Min Range: -6.5568
Max Act: 5.6818. Min Act: -0.1700
Data Index: 7390179 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5568. Min Range: -6.5568
Max Act: 5.6193. Min Act: -0.1700
Data Index: 7125523 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5568. Min Range: -6.5568
Max Act: 5.6193. Min Act: -0.1700
Data Index: 4476081 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5568. Min Range: -6.5568
Max Act: 5.6505. Min Act: -0.1700
Data Index: 5711022 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5568. Min Range: -6.5568
Max Act: 5.5568. Min Act: -0.1700
Data Index: 5710779 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5568. Min Range: -6.5568
Max Act: 5.4943. Min Act: -0.1700
Data Index: 6247238 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5568. Min Range: -6.5568
Max Act: 5.4630. Min Act: -0.1700
Data Index: 5885514 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5568. Min Range: -6.5568
Max Act: 5.4318. Min Act: -0.1700
Data Index: 6005263 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5568. Min Range: -6.5568
Max Act: 5.4318. Min Act: -0.1700
Data Index: 1680932 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5568. Min Range: -6.5568
Max Act: 5.4318. Min Act: -0.1700
Data Index: 7960396 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5568. Min Range: -6.5568
Max Act: 5.4005. Min Act: -0.1700
Data Index: 4051265 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5568. Min Range: -6.5568
Max Act: 5.4005. Min Act: -0.1700
Data Index: 445437 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5568. Min Range: -6.5568
Max Act: 5.4005. Min Act: -0.1700
Data Index: 4621544 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5568. Min Range: -6.5568
Max Act: 5.3693. Min Act: -0.1700
Data Index: 7495109 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5568. Min Range: -6.5568
Max Act: 5.3380. Min Act: -0.1700
Data Index: 1028206 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5568. Min Range: -6.5568
Max Act: 5.3693. Min Act: -0.1700
Data Index: 3058613 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5568. Min Range: -6.5568
Max Act: 5.3380. Min Act: -0.1700
Data Index: 6196676 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5568. Min Range: -6.5568
Max Act: 5.2755. Min Act: -0.1700
Data Index: 7542768 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5568. Min Range: -6.5568
Max Act: 5.3068. Min Act: -0.1700
Data Index: 4460356 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #19