Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3604 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1848. Min Range: -5.1848
Max Act: 5.1848. Min Act: -0.1700
Data Index: 1688008 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1848. Min Range: -5.1848
Max Act: 5.1223. Min Act: -0.1700
Data Index: 4140724 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1848. Min Range: -5.1848
Max Act: 5.0598. Min Act: -0.1700
Data Index: 3449451 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1848. Min Range: -5.1848
Max Act: 4.9973. Min Act: -0.1700
Data Index: 1923198 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1848. Min Range: -5.1848
Max Act: 4.9348. Min Act: -0.1700
Data Index: 81116 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1848. Min Range: -5.1848
Max Act: 4.8723. Min Act: -0.1700
Data Index: 4129466 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1848. Min Range: -5.1848
Max Act: 4.8410. Min Act: -0.1700
Data Index: 8223946 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1848. Min Range: -5.1848
Max Act: 4.8410. Min Act: -0.1700
Data Index: 295845 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1848. Min Range: -5.1848
Max Act: 4.9035. Min Act: -0.1700
Data Index: 7827577 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1848. Min Range: -5.1848
Max Act: 4.8410. Min Act: -0.1700
Data Index: 1154184 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1848. Min Range: -5.1848
Max Act: 4.8098. Min Act: -0.1700
Data Index: 8011941 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1848. Min Range: -5.1848
Max Act: 4.8098. Min Act: -0.1700
Data Index: 714046 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1848. Min Range: -5.1848
Max Act: 4.8098. Min Act: -0.1700
Data Index: 3069640 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1848. Min Range: -5.1848
Max Act: 4.8098. Min Act: -0.1700
Data Index: 7334599 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1848. Min Range: -5.1848
Max Act: 4.7785. Min Act: -0.1700
Data Index: 1912372 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1848. Min Range: -5.1848
Max Act: 4.7785. Min Act: -0.1700
Data Index: 1673145 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1848. Min Range: -5.1848
Max Act: 4.7785. Min Act: -0.1700
Data Index: 1432260 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1848. Min Range: -5.1848
Max Act: 4.7473. Min Act: -0.1700
Data Index: 5697630 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1848. Min Range: -5.1848
Max Act: 4.7785. Min Act: -0.1700
Data Index: 1026441 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1848. Min Range: -5.1848
Max Act: 4.7473. Min Act: -0.1700
Data Index: 272866 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19