Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3396 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7296. Min Range: -6.7296
Max Act: 6.7296. Min Act: -0.1700
Data Index: 3342114 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7296. Min Range: -6.7296
Max Act: 6.5733. Min Act: -0.1700
Data Index: 5851087 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7296. Min Range: -6.7296
Max Act: 6.5421. Min Act: -0.1700
Data Index: 3128047 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7296. Min Range: -6.7296
Max Act: 6.3546. Min Act: -0.1700
Data Index: 8503667 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7296. Min Range: -6.7296
Max Act: 6.3233. Min Act: -0.1700
Data Index: 2913070 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7296. Min Range: -6.7296
Max Act: 6.3233. Min Act: -0.1700
Data Index: 499383 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7296. Min Range: -6.7296
Max Act: 6.2608. Min Act: -0.1700
Data Index: 1543774 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7296. Min Range: -6.7296
Max Act: 6.2296. Min Act: -0.1700
Data Index: 1565160 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7296. Min Range: -6.7296
Max Act: 6.2296. Min Act: -0.1700
Data Index: 3414305 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7296. Min Range: -6.7296
Max Act: 6.1983. Min Act: -0.1700
Data Index: 6019187 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7296. Min Range: -6.7296
Max Act: 6.2296. Min Act: -0.1700
Data Index: 1460533 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7296. Min Range: -6.7296
Max Act: 6.1983. Min Act: -0.1700
Data Index: 7423725 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7296. Min Range: -6.7296
Max Act: 6.1671. Min Act: -0.1700
Data Index: 3329486 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7296. Min Range: -6.7296
Max Act: 6.1983. Min Act: -0.1700
Data Index: 8081923 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7296. Min Range: -6.7296
Max Act: 6.1983. Min Act: -0.1700
Data Index: 1551958 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7296. Min Range: -6.7296
Max Act: 6.1983. Min Act: -0.1700
Data Index: 6197316 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7296. Min Range: -6.7296
Max Act: 6.1671. Min Act: -0.1700
Data Index: 3152316 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7296. Min Range: -6.7296
Max Act: 6.1671. Min Act: -0.1700
Data Index: 2085162 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7296. Min Range: -6.7296
Max Act: 6.1358. Min Act: -0.1700
Data Index: 3750330 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7296. Min Range: -6.7296
Max Act: 6.1358. Min Act: -0.1700
Data Index: 3649398 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19