Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3755 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8665. Min Range: -3.8665
Max Act: 3.8665. Min Act: -0.1700
Data Index: 1821529 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8665. Min Range: -3.8665
Max Act: 3.8665. Min Act: -0.1700
Data Index: 6803544 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8665. Min Range: -3.8665
Max Act: 3.8665. Min Act: -0.1700
Data Index: 6361509 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8665. Min Range: -3.8665
Max Act: 3.8040. Min Act: -0.1700
Data Index: 3319215 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8665. Min Range: -3.8665
Max Act: 3.8040. Min Act: -0.1700
Data Index: 8241485 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8665. Min Range: -3.8665
Max Act: 3.7101. Min Act: -0.1700
Data Index: 6663454 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8665. Min Range: -3.8665
Max Act: 3.6945. Min Act: -0.1700
Data Index: 2038866 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8665. Min Range: -3.8665
Max Act: 3.6475. Min Act: -0.1700
Data Index: 763127 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8665. Min Range: -3.8665
Max Act: 3.6632. Min Act: -0.1700
Data Index: 5866809 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8665. Min Range: -3.8665
Max Act: 3.6006. Min Act: -0.1700
Data Index: 2687406 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8665. Min Range: -3.8665
Max Act: 3.6162. Min Act: -0.1700
Data Index: 1030473 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8665. Min Range: -3.8665
Max Act: 3.6006. Min Act: -0.1700
Data Index: 5330697 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8665. Min Range: -3.8665
Max Act: 3.6319. Min Act: -0.1700
Data Index: 243845 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8665. Min Range: -3.8665
Max Act: 3.6162. Min Act: -0.1700
Data Index: 8072628 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8665. Min Range: -3.8665
Max Act: 3.6632. Min Act: -0.1700
Data Index: 7880259 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8665. Min Range: -3.8665
Max Act: 3.5693. Min Act: -0.1700
Data Index: 6844785 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8665. Min Range: -3.8665
Max Act: 3.6006. Min Act: -0.1700
Data Index: 8417675 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8665. Min Range: -3.8665
Max Act: 3.5693. Min Act: -0.1700
Data Index: 8628053 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8665. Min Range: -3.8665
Max Act: 3.5536. Min Act: -0.1700
Data Index: 4959698 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8665. Min Range: -3.8665
Max Act: 3.5693. Min Act: -0.1700
Data Index: 707538 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19