Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3392 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6792. Min Range: -4.6792
Max Act: 4.6792. Min Act: -0.1700
Data Index: 7223038 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6792. Min Range: -4.6792
Max Act: 4.6167. Min Act: -0.1700
Data Index: 2887741 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6792. Min Range: -4.6792
Max Act: 4.5542. Min Act: -0.1700
Data Index: 5411428 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6792. Min Range: -4.6792
Max Act: 4.5854. Min Act: -0.1700
Data Index: 2462759 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6792. Min Range: -4.6792
Max Act: 4.4917. Min Act: -0.1700
Data Index: 4263263 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6792. Min Range: -4.6792
Max Act: 4.3979. Min Act: -0.1700
Data Index: 4577917 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6792. Min Range: -4.6792
Max Act: 4.3979. Min Act: -0.1700
Data Index: 1980875 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6792. Min Range: -4.6792
Max Act: 4.4292. Min Act: -0.1700
Data Index: 3293751 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6792. Min Range: -4.6792
Max Act: 4.3979. Min Act: -0.1700
Data Index: 2270819 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6792. Min Range: -4.6792
Max Act: 4.3979. Min Act: -0.1700
Data Index: 3486225 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6792. Min Range: -4.6792
Max Act: 4.3667. Min Act: -0.1700
Data Index: 7291485 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6792. Min Range: -4.6792
Max Act: 4.3667. Min Act: -0.1700
Data Index: 4327301 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6792. Min Range: -4.6792
Max Act: 4.3667. Min Act: -0.1700
Data Index: 4118891 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6792. Min Range: -4.6792
Max Act: 4.3354. Min Act: -0.1700
Data Index: 8341472 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6792. Min Range: -4.6792
Max Act: 4.3042. Min Act: -0.1700
Data Index: 1572548 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6792. Min Range: -4.6792
Max Act: 4.3042. Min Act: -0.1700
Data Index: 1499848 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6792. Min Range: -4.6792
Max Act: 4.3042. Min Act: -0.1700
Data Index: 699449 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6792. Min Range: -4.6792
Max Act: 4.3354. Min Act: -0.1700
Data Index: 2973565 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6792. Min Range: -4.6792
Max Act: 4.2417. Min Act: -0.1700
Data Index: 5159758 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6792. Min Range: -4.6792
Max Act: 4.2729. Min Act: -0.1700
Data Index: 3096917 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19