Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 24 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9167. Min Range: -3.9167
Max Act: 3.9167. Min Act: -0.1700
Data Index: 6856734 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9167. Min Range: -3.9167
Max Act: 3.8229. Min Act: -0.1700
Data Index: 4255028 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9167. Min Range: -3.9167
Max Act: 3.7916. Min Act: -0.1700
Data Index: 7889124 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9167. Min Range: -3.9167
Max Act: 3.7603. Min Act: -0.1700
Data Index: 6009686 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9167. Min Range: -3.9167
Max Act: 3.6978. Min Act: -0.1700
Data Index: 5013901 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9167. Min Range: -3.9167
Max Act: 3.6978. Min Act: -0.1700
Data Index: 7069767 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9167. Min Range: -3.9167
Max Act: 3.6978. Min Act: -0.1700
Data Index: 4901178 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9167. Min Range: -3.9167
Max Act: 3.6665. Min Act: -0.1700
Data Index: 4646944 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9167. Min Range: -3.9167
Max Act: 3.6821. Min Act: -0.1700
Data Index: 514577 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9167. Min Range: -3.9167
Max Act: 3.6508. Min Act: -0.1700
Data Index: 6856722 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9167. Min Range: -3.9167
Max Act: 3.6508. Min Act: -0.1700
Data Index: 5960467 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9167. Min Range: -3.9167
Max Act: 3.6508. Min Act: -0.1700
Data Index: 6176900 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9167. Min Range: -3.9167
Max Act: 3.6508. Min Act: -0.1700
Data Index: 6856736 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9167. Min Range: -3.9167
Max Act: 3.6352. Min Act: -0.1700
Data Index: 4947882 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9167. Min Range: -3.9167
Max Act: 3.6352. Min Act: -0.1700
Data Index: 5634677 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9167. Min Range: -3.9167
Max Act: 3.6352. Min Act: -0.1700
Data Index: 226001 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9167. Min Range: -3.9167
Max Act: 3.6195. Min Act: -0.1700
Data Index: 5064724 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9167. Min Range: -3.9167
Max Act: 3.5882. Min Act: -0.1700
Data Index: 1878898 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9167. Min Range: -3.9167
Max Act: 3.6039. Min Act: -0.1700
Data Index: 4844087 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9167. Min Range: -3.9167
Max Act: 3.6039. Min Act: -0.1700
Data Index: 5984034 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19