Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3529 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8785. Min Range: -5.8785
Max Act: 5.8785. Min Act: -0.1700
Data Index: 1227251 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8785. Min Range: -5.8785
Max Act: 5.6910. Min Act: -0.1700
Data Index: 311538 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8785. Min Range: -5.8785
Max Act: 5.5348. Min Act: -0.1700
Data Index: 3810062 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8785. Min Range: -5.8785
Max Act: 5.4098. Min Act: -0.1700
Data Index: 4084857 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8785. Min Range: -5.8785
Max Act: 5.3160. Min Act: -0.1700
Data Index: 8684384 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8785. Min Range: -5.8785
Max Act: 5.2848. Min Act: -0.1700
Data Index: 2361811 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8785. Min Range: -5.8785
Max Act: 5.3160. Min Act: -0.1700
Data Index: 3835922 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8785. Min Range: -5.8785
Max Act: 5.2535. Min Act: -0.1700
Data Index: 1929700 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8785. Min Range: -5.8785
Max Act: 5.2223. Min Act: -0.1700
Data Index: 6965988 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8785. Min Range: -5.8785
Max Act: 5.2223. Min Act: -0.1700
Data Index: 2696603 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8785. Min Range: -5.8785
Max Act: 5.1598. Min Act: -0.1700
Data Index: 5621195 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8785. Min Range: -5.8785
Max Act: 5.1910. Min Act: -0.1700
Data Index: 4958912 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8785. Min Range: -5.8785
Max Act: 5.1598. Min Act: -0.1700
Data Index: 2347981 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8785. Min Range: -5.8785
Max Act: 5.1910. Min Act: -0.1700
Data Index: 965972 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8785. Min Range: -5.8785
Max Act: 5.1285. Min Act: -0.1700
Data Index: 1300683 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8785. Min Range: -5.8785
Max Act: 5.1285. Min Act: -0.1700
Data Index: 548636 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8785. Min Range: -5.8785
Max Act: 5.0660. Min Act: -0.1700
Data Index: 2087768 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8785. Min Range: -5.8785
Max Act: 5.0660. Min Act: -0.1700
Data Index: 3820156 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8785. Min Range: -5.8785
Max Act: 5.0973. Min Act: -0.1700
Data Index: 259563 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8785. Min Range: -5.8785
Max Act: 5.0660. Min Act: -0.1700
Data Index: 507077 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19