Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2740 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5858. Min Range: -5.5858
Max Act: 5.5858. Min Act: -0.1700
Data Index: 7533380 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5858. Min Range: -5.5858
Max Act: 5.5233. Min Act: -0.1700
Data Index: 5522865 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5858. Min Range: -5.5858
Max Act: 5.3983. Min Act: -0.1700
Data Index: 2911598 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5858. Min Range: -5.5858
Max Act: 5.3671. Min Act: -0.1700
Data Index: 2911599 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5858. Min Range: -5.5858
Max Act: 5.3046. Min Act: -0.1700
Data Index: 789124 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5858. Min Range: -5.5858
Max Act: 5.2733. Min Act: -0.1700
Data Index: 1688902 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5858. Min Range: -5.5858
Max Act: 5.2421. Min Act: -0.1700
Data Index: 941361 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5858. Min Range: -5.5858
Max Act: 5.2421. Min Act: -0.1700
Data Index: 914194 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5858. Min Range: -5.5858
Max Act: 5.2108. Min Act: -0.1700
Data Index: 7920385 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5858. Min Range: -5.5858
Max Act: 5.1796. Min Act: -0.1700
Data Index: 6477400 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5858. Min Range: -5.5858
Max Act: 5.1483. Min Act: -0.1700
Data Index: 7110837 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5858. Min Range: -5.5858
Max Act: 5.1483. Min Act: -0.1700
Data Index: 8492751 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5858. Min Range: -5.5858
Max Act: 5.1483. Min Act: -0.1700
Data Index: 6595412 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5858. Min Range: -5.5858
Max Act: 5.1171. Min Act: -0.1700
Data Index: 7236643 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5858. Min Range: -5.5858
Max Act: 5.1483. Min Act: -0.1700
Data Index: 537852 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5858. Min Range: -5.5858
Max Act: 5.1171. Min Act: -0.1700
Data Index: 7953450 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5858. Min Range: -5.5858
Max Act: 5.1171. Min Act: -0.1700
Data Index: 4314616 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5858. Min Range: -5.5858
Max Act: 5.1171. Min Act: -0.1700
Data Index: 1130839 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5858. Min Range: -5.5858
Max Act: 5.1171. Min Act: -0.1700
Data Index: 6834785 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5858. Min Range: -5.5858
Max Act: 5.1171. Min Act: -0.1700
Data Index: 8204629 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19