Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3605 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0824. Min Range: -7.0824
Max Act: 7.0824. Min Act: -0.1700
Data Index: 8550344 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0824. Min Range: -7.0824
Max Act: 7.0824. Min Act: -0.1700
Data Index: 4773626 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0824. Min Range: -7.0824
Max Act: 6.9886. Min Act: -0.1700
Data Index: 6167996 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0824. Min Range: -7.0824
Max Act: 6.9261. Min Act: -0.1700
Data Index: 4819898 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0824. Min Range: -7.0824
Max Act: 6.9574. Min Act: -0.1700
Data Index: 6532193 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0824. Min Range: -7.0824
Max Act: 6.8949. Min Act: -0.1700
Data Index: 5464957 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0824. Min Range: -7.0824
Max Act: 6.8949. Min Act: -0.1700
Data Index: 6978072 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0824. Min Range: -7.0824
Max Act: 6.8636. Min Act: -0.1700
Data Index: 477385 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0824. Min Range: -7.0824
Max Act: 6.8636. Min Act: -0.1700
Data Index: 575261 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0824. Min Range: -7.0824
Max Act: 6.8011. Min Act: -0.1700
Data Index: 8671773 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0824. Min Range: -7.0824
Max Act: 6.8011. Min Act: -0.1700
Data Index: 3966456 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0824. Min Range: -7.0824
Max Act: 6.7699. Min Act: -0.1700
Data Index: 7382918 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0824. Min Range: -7.0824
Max Act: 6.7699. Min Act: -0.1700
Data Index: 7426860 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0824. Min Range: -7.0824
Max Act: 6.7699. Min Act: -0.1700
Data Index: 1191462 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0824. Min Range: -7.0824
Max Act: 6.7699. Min Act: -0.1700
Data Index: 4912053 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0824. Min Range: -7.0824
Max Act: 6.7699. Min Act: -0.1700
Data Index: 2515551 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0824. Min Range: -7.0824
Max Act: 6.7386. Min Act: -0.1700
Data Index: 7495986 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0824. Min Range: -7.0824
Max Act: 6.7074. Min Act: -0.1700
Data Index: 6354771 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0824. Min Range: -7.0824
Max Act: 6.7074. Min Act: -0.1700
Data Index: 6183101 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0824. Min Range: -7.0824
Max Act: 6.7074. Min Act: -0.1700
Data Index: 192546 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19