Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1651 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.4020. Min Act: -0.1700
Data Index: 8569901 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.4020. Min Act: -0.1700
Data Index: 8343324 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.4020. Min Act: -0.1700
Data Index: 1760663 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.3708. Min Act: -0.1700
Data Index: 7830661 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.4020. Min Act: -0.1700
Data Index: 5003594 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.4020. Min Act: -0.1700
Data Index: 3110277 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.3708. Min Act: -0.1700
Data Index: 8182789 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.3395. Min Act: -0.1700
Data Index: 4537786 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.3395. Min Act: -0.1700
Data Index: 4569804 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.3395. Min Act: -0.1700
Data Index: 3348465 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.3083. Min Act: -0.1700
Data Index: 4165378 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.3083. Min Act: -0.1700
Data Index: 8795987 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.3395. Min Act: -0.1700
Data Index: 7062441 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.3083. Min Act: -0.1700
Data Index: 7318037 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.3083. Min Act: -0.1700
Data Index: 5457303 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.2770. Min Act: -0.1700
Data Index: 8301572 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.2458. Min Act: -0.1700
Data Index: 277433 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4020. Min Range: -6.4020
Max Act: 5.9645. Min Act: -0.1700
Data Index: 2025636 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4020. Min Range: -6.4020
Max Act: 5.8708. Min Act: -0.1700
Data Index: 5354760 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4020. Min Range: -6.4020
Max Act: 5.8395. Min Act: -0.1700
Data Index: 2299397 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19