Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2217 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8585. Min Range: -2.8585
Max Act: 2.8585. Min Act: -0.1700
Data Index: 5471516 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8585. Min Range: -2.8585
Max Act: 2.8108. Min Act: -0.1700
Data Index: 5251940 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8585. Min Range: -2.8585
Max Act: 2.7949. Min Act: -0.1700
Data Index: 1941178 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8585. Min Range: -2.8585
Max Act: 2.7789. Min Act: -0.1700
Data Index: 6567705 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8585. Min Range: -2.8585
Max Act: 2.7630. Min Act: -0.1700
Data Index: 7332493 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8585. Min Range: -2.8585
Max Act: 2.7630. Min Act: -0.1700
Data Index: 1831602 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8585. Min Range: -2.8585
Max Act: 2.7630. Min Act: -0.1700
Data Index: 4659939 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8585. Min Range: -2.8585
Max Act: 2.7470. Min Act: -0.1700
Data Index: 5134224 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8585. Min Range: -2.8585
Max Act: 2.7151. Min Act: -0.1700
Data Index: 7838066 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8585. Min Range: -2.8585
Max Act: 2.7310. Min Act: -0.1700
Data Index: 8667192 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8585. Min Range: -2.8585
Max Act: 2.7470. Min Act: -0.1700
Data Index: 2725697 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8585. Min Range: -2.8585
Max Act: 2.7151. Min Act: -0.1700
Data Index: 6502899 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8585. Min Range: -2.8585
Max Act: 2.7310. Min Act: -0.1700
Data Index: 5251941 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8585. Min Range: -2.8585
Max Act: 2.7151. Min Act: -0.1700
Data Index: 5224245 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8585. Min Range: -2.8585
Max Act: 2.7151. Min Act: -0.1700
Data Index: 390718 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8585. Min Range: -2.8585
Max Act: 2.6991. Min Act: -0.1700
Data Index: 4354208 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8585. Min Range: -2.8585
Max Act: 2.7151. Min Act: -0.1700
Data Index: 857080 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8585. Min Range: -2.8585
Max Act: 2.7151. Min Act: -0.1700
Data Index: 2435362 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8585. Min Range: -2.8585
Max Act: 2.6991. Min Act: -0.1700
Data Index: 685023 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8585. Min Range: -2.8585
Max Act: 2.6991. Min Act: -0.1700
Data Index: 7075023 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19