Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3506 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5693. Min Range: -3.5693
Max Act: 3.5693. Min Act: -0.1700
Data Index: 24097 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5693. Min Range: -3.5693
Max Act: 3.5380. Min Act: -0.1700
Data Index: 3034102 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5693. Min Range: -3.5693
Max Act: 3.5224. Min Act: -0.1700
Data Index: 2997295 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5693. Min Range: -3.5693
Max Act: 3.5067. Min Act: -0.1700
Data Index: 6745435 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5693. Min Range: -3.5693
Max Act: 3.4754. Min Act: -0.1700
Data Index: 7625215 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5693. Min Range: -3.5693
Max Act: 3.4754. Min Act: -0.1700
Data Index: 193907 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5693. Min Range: -3.5693
Max Act: 3.4440. Min Act: -0.1700
Data Index: 8304187 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5693. Min Range: -3.5693
Max Act: 3.4284. Min Act: -0.1700
Data Index: 3322022 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5693. Min Range: -3.5693
Max Act: 3.4284. Min Act: -0.1700
Data Index: 2742080 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5693. Min Range: -3.5693
Max Act: 3.3970. Min Act: -0.1700
Data Index: 1804303 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5693. Min Range: -3.5693
Max Act: 3.4127. Min Act: -0.1700
Data Index: 3949816 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5693. Min Range: -3.5693
Max Act: 3.3656. Min Act: -0.1700
Data Index: 3122825 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5693. Min Range: -3.5693
Max Act: 3.3656. Min Act: -0.1700
Data Index: 306938 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5693. Min Range: -3.5693
Max Act: 3.3500. Min Act: -0.1700
Data Index: 3081047 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5693. Min Range: -3.5693
Max Act: 3.3343. Min Act: -0.1700
Data Index: 4622714 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5693. Min Range: -3.5693
Max Act: 3.3343. Min Act: -0.1700
Data Index: 4078014 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5693. Min Range: -3.5693
Max Act: 3.3343. Min Act: -0.1700
Data Index: 1740210 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5693. Min Range: -3.5693
Max Act: 3.3029. Min Act: -0.1700
Data Index: 3981922 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5693. Min Range: -3.5693
Max Act: 3.3186. Min Act: -0.1700
Data Index: 7386675 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5693. Min Range: -3.5693
Max Act: 3.3343. Min Act: -0.1700
Data Index: 7959828 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19