Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3602 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.9869. Min Act: -0.1700
Data Index: 4480685 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.9244. Min Act: -0.1700
Data Index: 5556507 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.8932. Min Act: -0.1700
Data Index: 8177545 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.8619. Min Act: -0.1700
Data Index: 4480860 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.8307. Min Act: -0.1700
Data Index: 5499221 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.8307. Min Act: -0.1700
Data Index: 4700273 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7994. Min Act: -0.1700
Data Index: 2534561 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7682. Min Act: -0.1700
Data Index: 4019576 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7994. Min Act: -0.1700
Data Index: 2520677 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7057. Min Act: -0.1700
Data Index: 7698418 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7057. Min Act: -0.1700
Data Index: 8114329 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.6744. Min Act: -0.1700
Data Index: 6451489 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7057. Min Act: -0.1700
Data Index: 3346459 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.6744. Min Act: -0.1700
Data Index: 145071 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.6744. Min Act: -0.1700
Data Index: 1827528 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.6744. Min Act: -0.1700
Data Index: 1895629 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.6432. Min Act: -0.1700
Data Index: 702362 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.6432. Min Act: -0.1700
Data Index: 1291139 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.6432. Min Act: -0.1700
Data Index: 7274854 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.6432. Min Act: -0.1700
Data Index: 258004 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19