Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3416 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6308. Min Range: -5.6308
Max Act: 5.6308. Min Act: -0.1700
Data Index: 5786724 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6308. Min Range: -5.6308
Max Act: 5.6308. Min Act: -0.1700
Data Index: 2064163 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6308. Min Range: -5.6308
Max Act: 5.6308. Min Act: -0.1700
Data Index: 2530465 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6308. Min Range: -5.6308
Max Act: 5.5995. Min Act: -0.1700
Data Index: 2413472 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6308. Min Range: -5.6308
Max Act: 5.5995. Min Act: -0.1700
Data Index: 313475 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6308. Min Range: -5.6308
Max Act: 5.5683. Min Act: -0.1700
Data Index: 4424882 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6308. Min Range: -5.6308
Max Act: 5.5370. Min Act: -0.1700
Data Index: 5185853 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6308. Min Range: -5.6308
Max Act: 5.5683. Min Act: -0.1700
Data Index: 6487901 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6308. Min Range: -5.6308
Max Act: 5.5683. Min Act: -0.1700
Data Index: 4263511 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6308. Min Range: -5.6308
Max Act: 5.5370. Min Act: -0.1700
Data Index: 414720 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6308. Min Range: -5.6308
Max Act: 5.5058. Min Act: -0.1700
Data Index: 2107014 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6308. Min Range: -5.6308
Max Act: 5.5058. Min Act: -0.1700
Data Index: 6959213 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6308. Min Range: -5.6308
Max Act: 5.5058. Min Act: -0.1700
Data Index: 2787956 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6308. Min Range: -5.6308
Max Act: 5.5058. Min Act: -0.1700
Data Index: 7802956 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6308. Min Range: -5.6308
Max Act: 5.4745. Min Act: -0.1700
Data Index: 5751282 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6308. Min Range: -5.6308
Max Act: 5.5370. Min Act: -0.1700
Data Index: 307792 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6308. Min Range: -5.6308
Max Act: 5.5058. Min Act: -0.1700
Data Index: 2989769 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6308. Min Range: -5.6308
Max Act: 5.4745. Min Act: -0.1700
Data Index: 2258907 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6308. Min Range: -5.6308
Max Act: 5.4433. Min Act: -0.1700
Data Index: 1643382 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6308. Min Range: -5.6308
Max Act: 5.4120. Min Act: -0.1700
Data Index: 6801014 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19