Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3212 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9282. Min Range: -6.9282
Max Act: 6.9282. Min Act: -0.1700
Data Index: 2225250 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9282. Min Range: -6.9282
Max Act: 6.8657. Min Act: -0.1700
Data Index: 4464987 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9282. Min Range: -6.9282
Max Act: 6.8970. Min Act: -0.1700
Data Index: 2035147 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9282. Min Range: -6.9282
Max Act: 6.7720. Min Act: -0.1700
Data Index: 545283 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9282. Min Range: -6.9282
Max Act: 6.7407. Min Act: -0.1700
Data Index: 561858 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9282. Min Range: -6.9282
Max Act: 6.6782. Min Act: -0.1700
Data Index: 670635 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9282. Min Range: -6.9282
Max Act: 6.6782. Min Act: -0.1700
Data Index: 675815 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9282. Min Range: -6.9282
Max Act: 6.6782. Min Act: -0.1700
Data Index: 7076348 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9282. Min Range: -6.9282
Max Act: 6.6470. Min Act: -0.1700
Data Index: 1363978 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9282. Min Range: -6.9282
Max Act: 6.6470. Min Act: -0.1700
Data Index: 5600245 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9282. Min Range: -6.9282
Max Act: 6.6157. Min Act: -0.1700
Data Index: 2601635 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9282. Min Range: -6.9282
Max Act: 6.6157. Min Act: -0.1700
Data Index: 1938628 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9282. Min Range: -6.9282
Max Act: 6.5845. Min Act: -0.1700
Data Index: 5710206 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9282. Min Range: -6.9282
Max Act: 6.5845. Min Act: -0.1700
Data Index: 574650 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9282. Min Range: -6.9282
Max Act: 6.5532. Min Act: -0.1700
Data Index: 459727 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9282. Min Range: -6.9282
Max Act: 6.5532. Min Act: -0.1700
Data Index: 4329179 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9282. Min Range: -6.9282
Max Act: 6.5532. Min Act: -0.1700
Data Index: 5484572 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9282. Min Range: -6.9282
Max Act: 6.5532. Min Act: -0.1700
Data Index: 1525904 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9282. Min Range: -6.9282
Max Act: 6.5220. Min Act: -0.1700
Data Index: 4812315 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9282. Min Range: -6.9282
Max Act: 6.5532. Min Act: -0.1700
Data Index: 5098347 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #19