Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2359 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.5495. Min Range: -10.5495
Max Act: 10.5495. Min Act: -0.1700
Data Index: 3371541 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5495. Min Range: -10.5495
Max Act: 10.4245. Min Act: -0.1700
Data Index: 5187382 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5495. Min Range: -10.5495
Max Act: 10.0495. Min Act: -0.1700
Data Index: 4190517 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5495. Min Range: -10.5495
Max Act: 10.1745. Min Act: -0.1700
Data Index: 1632539 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5495. Min Range: -10.5495
Max Act: 9.9870. Min Act: -0.1700
Data Index: 6527495 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5495. Min Range: -10.5495
Max Act: 10.0495. Min Act: -0.1700
Data Index: 6848533 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5495. Min Range: -10.5495
Max Act: 9.9870. Min Act: -0.1700
Data Index: 7038711 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5495. Min Range: -10.5495
Max Act: 9.7995. Min Act: -0.1700
Data Index: 6002688 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5495. Min Range: -10.5495
Max Act: 9.8620. Min Act: -0.1700
Data Index: 6512378 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5495. Min Range: -10.5495
Max Act: 9.8620. Min Act: -0.1700
Data Index: 2697094 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5495. Min Range: -10.5495
Max Act: 9.7370. Min Act: -0.1700
Data Index: 2846461 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5495. Min Range: -10.5495
Max Act: 9.7995. Min Act: -0.1700
Data Index: 6502918 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5495. Min Range: -10.5495
Max Act: 9.7995. Min Act: -0.1700
Data Index: 6795551 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5495. Min Range: -10.5495
Max Act: 9.9245. Min Act: -0.1700
Data Index: 4552766 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5495. Min Range: -10.5495
Max Act: 9.7370. Min Act: -0.1700
Data Index: 151209 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5495. Min Range: -10.5495
Max Act: 9.8620. Min Act: -0.1700
Data Index: 5847987 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5495. Min Range: -10.5495
Max Act: 9.7995. Min Act: -0.1700
Data Index: 2954046 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5495. Min Range: -10.5495
Max Act: 9.7370. Min Act: -0.1700
Data Index: 6341687 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5495. Min Range: -10.5495
Max Act: 9.7370. Min Act: -0.1700
Data Index: 3371888 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5495. Min Range: -10.5495
Max Act: 9.6120. Min Act: -0.1700
Data Index: 781273 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #19