Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4872 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3339. Min Range: -5.3339
Max Act: 5.3339. Min Act: -0.1700
Data Index: 2226978 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3339. Min Range: -5.3339
Max Act: 5.1151. Min Act: -0.1700
Data Index: 627387 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3339. Min Range: -5.3339
Max Act: 4.8964. Min Act: -0.1700
Data Index: 4662579 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3339. Min Range: -5.3339
Max Act: 4.8651. Min Act: -0.1700
Data Index: 627393 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3339. Min Range: -5.3339
Max Act: 4.8651. Min Act: -0.1700
Data Index: 8265106 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3339. Min Range: -5.3339
Max Act: 4.7714. Min Act: -0.1700
Data Index: 5623554 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3339. Min Range: -5.3339
Max Act: 4.7714. Min Act: -0.1700
Data Index: 627394 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3339. Min Range: -5.3339
Max Act: 4.7714. Min Act: -0.1700
Data Index: 1995226 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3339. Min Range: -5.3339
Max Act: 4.8026. Min Act: -0.1700
Data Index: 436179 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3339. Min Range: -5.3339
Max Act: 4.7714. Min Act: -0.1700
Data Index: 3692920 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3339. Min Range: -5.3339
Max Act: 4.7714. Min Act: -0.1700
Data Index: 5639985 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3339. Min Range: -5.3339
Max Act: 4.7401. Min Act: -0.1700
Data Index: 627392 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3339. Min Range: -5.3339
Max Act: 4.7089. Min Act: -0.1700
Data Index: 7096161 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3339. Min Range: -5.3339
Max Act: 4.7401. Min Act: -0.1700
Data Index: 5361928 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3339. Min Range: -5.3339
Max Act: 4.7089. Min Act: -0.1700
Data Index: 8682505 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3339. Min Range: -5.3339
Max Act: 4.6776. Min Act: -0.1700
Data Index: 627390 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3339. Min Range: -5.3339
Max Act: 4.6464. Min Act: -0.1700
Data Index: 4388659 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3339. Min Range: -5.3339
Max Act: 4.6151. Min Act: -0.1700
Data Index: 155412 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3339. Min Range: -5.3339
Max Act: 4.6464. Min Act: -0.1700
Data Index: 4843043 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3339. Min Range: -5.3339
Max Act: 4.6464. Min Act: -0.1700
Data Index: 3863323 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19