Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3267 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9451. Min Range: -4.9451
Max Act: 4.9451. Min Act: -0.1700
Data Index: 594791 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9451. Min Range: -4.9451
Max Act: 4.9451. Min Act: -0.1700
Data Index: 2515843 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9451. Min Range: -4.9451
Max Act: 4.9139. Min Act: -0.1700
Data Index: 4064621 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9451. Min Range: -4.9451
Max Act: 4.8514. Min Act: -0.1700
Data Index: 7943274 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9451. Min Range: -4.9451
Max Act: 4.8514. Min Act: -0.1700
Data Index: 5147072 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9451. Min Range: -4.9451
Max Act: 4.8514. Min Act: -0.1700
Data Index: 8027807 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9451. Min Range: -4.9451
Max Act: 4.8201. Min Act: -0.1700
Data Index: 2113079 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9451. Min Range: -4.9451
Max Act: 4.8201. Min Act: -0.1700
Data Index: 320177 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9451. Min Range: -4.9451
Max Act: 4.7264. Min Act: -0.1700
Data Index: 2761369 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9451. Min Range: -4.9451
Max Act: 4.7576. Min Act: -0.1700
Data Index: 6487738 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9451. Min Range: -4.9451
Max Act: 4.7576. Min Act: -0.1700
Data Index: 6442681 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9451. Min Range: -4.9451
Max Act: 4.7576. Min Act: -0.1700
Data Index: 646858 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9451. Min Range: -4.9451
Max Act: 4.7576. Min Act: -0.1700
Data Index: 8098569 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9451. Min Range: -4.9451
Max Act: 4.7576. Min Act: -0.1700
Data Index: 7943271 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9451. Min Range: -4.9451
Max Act: 4.7264. Min Act: -0.1700
Data Index: 7663499 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9451. Min Range: -4.9451
Max Act: 4.7264. Min Act: -0.1700
Data Index: 320180 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9451. Min Range: -4.9451
Max Act: 4.7264. Min Act: -0.1700
Data Index: 6827864 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9451. Min Range: -4.9451
Max Act: 4.7264. Min Act: -0.1700
Data Index: 1323643 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9451. Min Range: -4.9451
Max Act: 4.6951. Min Act: -0.1700
Data Index: 3509399 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9451. Min Range: -4.9451
Max Act: 4.7264. Min Act: -0.1700
Data Index: 7581037 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #19