Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5575 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2290. Min Range: -5.2290
Max Act: 5.2290. Min Act: -0.1700
Data Index: 7310643 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2290. Min Range: -5.2290
Max Act: 5.0102. Min Act: -0.1700
Data Index: 2505583 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2290. Min Range: -5.2290
Max Act: 4.9477. Min Act: -0.1700
Data Index: 1044294 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2290. Min Range: -5.2290
Max Act: 4.8540. Min Act: -0.1700
Data Index: 3808601 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2290. Min Range: -5.2290
Max Act: 4.7602. Min Act: -0.1700
Data Index: 1044292 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2290. Min Range: -5.2290
Max Act: 4.7290. Min Act: -0.1700
Data Index: 7096332 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2290. Min Range: -5.2290
Max Act: 4.6977. Min Act: -0.1700
Data Index: 4760678 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2290. Min Range: -5.2290
Max Act: 4.6977. Min Act: -0.1700
Data Index: 162506 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2290. Min Range: -5.2290
Max Act: 4.6977. Min Act: -0.1700
Data Index: 912913 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2290. Min Range: -5.2290
Max Act: 4.6977. Min Act: -0.1700
Data Index: 8678072 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2290. Min Range: -5.2290
Max Act: 4.6977. Min Act: -0.1700
Data Index: 7032982 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2290. Min Range: -5.2290
Max Act: 4.6665. Min Act: -0.1700
Data Index: 479461 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2290. Min Range: -5.2290
Max Act: 4.6352. Min Act: -0.1700
Data Index: 8657193 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2290. Min Range: -5.2290
Max Act: 4.6352. Min Act: -0.1700
Data Index: 5293566 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2290. Min Range: -5.2290
Max Act: 4.6352. Min Act: -0.1700
Data Index: 7844496 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2290. Min Range: -5.2290
Max Act: 4.6352. Min Act: -0.1700
Data Index: 4890435 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2290. Min Range: -5.2290
Max Act: 4.6040. Min Act: -0.1700
Data Index: 1044291 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2290. Min Range: -5.2290
Max Act: 4.6040. Min Act: -0.1700
Data Index: 3046742 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2290. Min Range: -5.2290
Max Act: 4.6040. Min Act: -0.1700
Data Index: 7850556 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2290. Min Range: -5.2290
Max Act: 4.6040. Min Act: -0.1700
Data Index: 6476375 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19