Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4509 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4500. Min Range: -6.4500
Max Act: 6.4500. Min Act: -0.1700
Data Index: 5051604 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4500. Min Range: -6.4500
Max Act: 6.3563. Min Act: -0.1700
Data Index: 1154525 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4500. Min Range: -6.4500
Max Act: 6.3563. Min Act: -0.1700
Data Index: 120502 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4500. Min Range: -6.4500
Max Act: 6.3250. Min Act: -0.1700
Data Index: 845215 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4500. Min Range: -6.4500
Max Act: 6.2938. Min Act: -0.1700
Data Index: 7952475 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4500. Min Range: -6.4500
Max Act: 6.2625. Min Act: -0.1700
Data Index: 5763747 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4500. Min Range: -6.4500
Max Act: 6.2625. Min Act: -0.1700
Data Index: 820394 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4500. Min Range: -6.4500
Max Act: 6.2313. Min Act: -0.1700
Data Index: 38509 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4500. Min Range: -6.4500
Max Act: 6.2000. Min Act: -0.1700
Data Index: 5487498 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4500. Min Range: -6.4500
Max Act: 6.2313. Min Act: -0.1700
Data Index: 5956344 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4500. Min Range: -6.4500
Max Act: 6.2000. Min Act: -0.1700
Data Index: 4812249 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4500. Min Range: -6.4500
Max Act: 6.2313. Min Act: -0.1700
Data Index: 1117156 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4500. Min Range: -6.4500
Max Act: 6.2000. Min Act: -0.1700
Data Index: 2410679 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4500. Min Range: -6.4500
Max Act: 6.2000. Min Act: -0.1700
Data Index: 8290194 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4500. Min Range: -6.4500
Max Act: 6.1375. Min Act: -0.1700
Data Index: 4660652 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4500. Min Range: -6.4500
Max Act: 6.1688. Min Act: -0.1700
Data Index: 6799467 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4500. Min Range: -6.4500
Max Act: 6.1375. Min Act: -0.1700
Data Index: 7038663 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4500. Min Range: -6.4500
Max Act: 6.1375. Min Act: -0.1700
Data Index: 3705669 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4500. Min Range: -6.4500
Max Act: 6.1063. Min Act: -0.1700
Data Index: 539611 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4500. Min Range: -6.4500
Max Act: 6.0750. Min Act: -0.1700
Data Index: 6505757 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19