Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 212 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0362. Min Range: -7.0362
Max Act: 7.0362. Min Act: -0.1700
Data Index: 3693246 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0362. Min Range: -7.0362
Max Act: 7.0362. Min Act: -0.1699
Data Index: 6812826 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0362. Min Range: -7.0362
Max Act: 6.9737. Min Act: -0.1700
Data Index: 6558594 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0362. Min Range: -7.0362
Max Act: 6.9737. Min Act: -0.1700
Data Index: 8153205 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0362. Min Range: -7.0362
Max Act: 6.9112. Min Act: -0.1700
Data Index: 558133 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0362. Min Range: -7.0362
Max Act: 6.9112. Min Act: -0.1700
Data Index: 121550 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0362. Min Range: -7.0362
Max Act: 6.9112. Min Act: -0.1700
Data Index: 1449425 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0362. Min Range: -7.0362
Max Act: 6.8800. Min Act: -0.1700
Data Index: 8199956 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0362. Min Range: -7.0362
Max Act: 6.8487. Min Act: -0.1700
Data Index: 2497263 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0362. Min Range: -7.0362
Max Act: 6.8487. Min Act: -0.1700
Data Index: 3951546 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0362. Min Range: -7.0362
Max Act: 6.8487. Min Act: -0.1700
Data Index: 581003 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0362. Min Range: -7.0362
Max Act: 6.8175. Min Act: -0.1700
Data Index: 4408139 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0362. Min Range: -7.0362
Max Act: 6.8175. Min Act: -0.1700
Data Index: 6162124 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0362. Min Range: -7.0362
Max Act: 6.8175. Min Act: -0.1699
Data Index: 8737466 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0362. Min Range: -7.0362
Max Act: 6.7862. Min Act: -0.1700
Data Index: 7708270 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0362. Min Range: -7.0362
Max Act: 6.7862. Min Act: -0.1700
Data Index: 1979956 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0362. Min Range: -7.0362
Max Act: 6.7862. Min Act: -0.1700
Data Index: 3204572 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0362. Min Range: -7.0362
Max Act: 6.7862. Min Act: -0.1700
Data Index: 4723558 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0362. Min Range: -7.0362
Max Act: 6.7550. Min Act: -0.1653
Data Index: 6110647 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0362. Min Range: -7.0362
Max Act: 6.7862. Min Act: -0.1700
Data Index: 828229 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19