Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2940 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.5001. Min Act: -0.1700
Data Index: 5381413 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.3438. Min Act: -0.1700
Data Index: 8132105 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.3438. Min Act: -0.1700
Data Index: 1811633 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.2813. Min Act: -0.1700
Data Index: 1486717 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.2501. Min Act: -0.1700
Data Index: 8712753 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.2501. Min Act: -0.1700
Data Index: 7362910 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.2501. Min Act: -0.1700
Data Index: 8671747 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.2188. Min Act: -0.1700
Data Index: 5465884 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.2188. Min Act: -0.1700
Data Index: 6590416 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.2188. Min Act: -0.1700
Data Index: 8013335 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.1251. Min Act: -0.1700
Data Index: 7415448 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.1251. Min Act: -0.1700
Data Index: 3807571 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.0938. Min Act: -0.1700
Data Index: 4526210 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.0626. Min Act: -0.1700
Data Index: 1526304 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.0626. Min Act: -0.1700
Data Index: 2162771 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.0313. Min Act: -0.1700
Data Index: 1735926 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.0001. Min Act: -0.1700
Data Index: 3449420 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.0313. Min Act: -0.1700
Data Index: 7250651 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.0001. Min Act: -0.1700
Data Index: 7098619 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.0313. Min Act: -0.1700
Data Index: 6595261 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #19