Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2405 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7322. Min Range: -7.7322
Max Act: 7.7322. Min Act: -0.1700
Data Index: 1369929 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7322. Min Range: -7.7322
Max Act: 7.1385. Min Act: -0.1700
Data Index: 8219107 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7322. Min Range: -7.7322
Max Act: 7.0447. Min Act: -0.1700
Data Index: 5178617 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7322. Min Range: -7.7322
Max Act: 6.9197. Min Act: -0.1700
Data Index: 4954351 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7322. Min Range: -7.7322
Max Act: 6.8885. Min Act: -0.1700
Data Index: 1425435 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7322. Min Range: -7.7322
Max Act: 6.8572. Min Act: -0.1700
Data Index: 6873304 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7322. Min Range: -7.7322
Max Act: 6.8885. Min Act: -0.1700
Data Index: 7360467 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7322. Min Range: -7.7322
Max Act: 6.8260. Min Act: -0.1700
Data Index: 1758206 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7322. Min Range: -7.7322
Max Act: 6.8260. Min Act: -0.1700
Data Index: 354205 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7322. Min Range: -7.7322
Max Act: 6.8260. Min Act: -0.1700
Data Index: 5759260 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7322. Min Range: -7.7322
Max Act: 6.7635. Min Act: -0.1700
Data Index: 2378467 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7322. Min Range: -7.7322
Max Act: 6.7322. Min Act: -0.1700
Data Index: 4760895 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7322. Min Range: -7.7322
Max Act: 6.7322. Min Act: -0.1700
Data Index: 5328277 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7322. Min Range: -7.7322
Max Act: 6.7322. Min Act: -0.1700
Data Index: 752557 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7322. Min Range: -7.7322
Max Act: 6.7010. Min Act: -0.1700
Data Index: 6299983 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7322. Min Range: -7.7322
Max Act: 6.6697. Min Act: -0.1700
Data Index: 8379332 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7322. Min Range: -7.7322
Max Act: 6.6385. Min Act: -0.1700
Data Index: 2149460 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7322. Min Range: -7.7322
Max Act: 6.6385. Min Act: -0.1700
Data Index: 4806953 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7322. Min Range: -7.7322
Max Act: 6.6072. Min Act: -0.1700
Data Index: 6808982 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7322. Min Range: -7.7322
Max Act: 6.6385. Min Act: -0.1700
Data Index: 4978466 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19