Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1706 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.9128. Min Act: -0.1700
Data Index: 1307180 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.9128. Min Act: -0.1700
Data Index: 4912034 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.8815. Min Act: -0.1700
Data Index: 3906850 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.8815. Min Act: -0.1700
Data Index: 2902823 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.8815. Min Act: -0.1700
Data Index: 2342364 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.8190. Min Act: -0.1700
Data Index: 8640507 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.8190. Min Act: -0.1700
Data Index: 7327767 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.8190. Min Act: -0.1700
Data Index: 2636872 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.7878. Min Act: -0.1700
Data Index: 142982 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.7878. Min Act: -0.1700
Data Index: 3427835 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.7565. Min Act: -0.1700
Data Index: 5111418 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.7565. Min Act: -0.1700
Data Index: 1546471 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.7253. Min Act: -0.1700
Data Index: 613036 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.7253. Min Act: -0.1700
Data Index: 4755599 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.6940. Min Act: -0.1700
Data Index: 6142837 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.6940. Min Act: -0.1700
Data Index: 400512 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.6940. Min Act: -0.1700
Data Index: 348867 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.7253. Min Act: -0.1700
Data Index: 456845 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.6940. Min Act: -0.1700
Data Index: 621780 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.6628. Min Act: -0.1700
Data Index: 2827174 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19