Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5846 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5542. Min Range: -7.5542
Max Act: 7.5542. Min Act: -0.1700
Data Index: 7236239 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5542. Min Range: -7.5542
Max Act: 7.3355. Min Act: -0.1700
Data Index: 5166629 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5542. Min Range: -7.5542
Max Act: 7.2417. Min Act: -0.1700
Data Index: 1083349 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5542. Min Range: -7.5542
Max Act: 7.1167. Min Act: -0.1700
Data Index: 3377145 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5542. Min Range: -7.5542
Max Act: 7.1480. Min Act: -0.1700
Data Index: 6765667 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5542. Min Range: -7.5542
Max Act: 7.1167. Min Act: -0.1700
Data Index: 6636351 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5542. Min Range: -7.5542
Max Act: 7.1167. Min Act: -0.1700
Data Index: 1172530 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5542. Min Range: -7.5542
Max Act: 7.0855. Min Act: -0.1700
Data Index: 222196 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5542. Min Range: -7.5542
Max Act: 7.0230. Min Act: -0.1700
Data Index: 541506 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5542. Min Range: -7.5542
Max Act: 7.0230. Min Act: -0.1700
Data Index: 5265027 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5542. Min Range: -7.5542
Max Act: 7.0230. Min Act: -0.1700
Data Index: 1886854 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5542. Min Range: -7.5542
Max Act: 7.0230. Min Act: -0.1700
Data Index: 1226706 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5542. Min Range: -7.5542
Max Act: 6.9605. Min Act: -0.1700
Data Index: 8785990 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5542. Min Range: -7.5542
Max Act: 6.8980. Min Act: -0.1700
Data Index: 5982378 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5542. Min Range: -7.5542
Max Act: 6.9292. Min Act: -0.1700
Data Index: 8743825 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5542. Min Range: -7.5542
Max Act: 6.8980. Min Act: -0.1700
Data Index: 2389817 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5542. Min Range: -7.5542
Max Act: 6.8980. Min Act: -0.1700
Data Index: 2732536 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5542. Min Range: -7.5542
Max Act: 6.8980. Min Act: -0.1700
Data Index: 7259418 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5542. Min Range: -7.5542
Max Act: 6.9292. Min Act: -0.1700
Data Index: 4681285 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5542. Min Range: -7.5542
Max Act: 6.8980. Min Act: -0.1700
Data Index: 4331626 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #19