Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2805 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7695. Min Range: -6.7695
Max Act: 6.7695. Min Act: -0.1700
Data Index: 4357485 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7695. Min Range: -6.7695
Max Act: 6.7382. Min Act: -0.1700
Data Index: 313931 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7695. Min Range: -6.7695
Max Act: 6.7382. Min Act: -0.1700
Data Index: 6558256 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7695. Min Range: -6.7695
Max Act: 6.7070. Min Act: -0.1700
Data Index: 4473033 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7695. Min Range: -6.7695
Max Act: 6.7070. Min Act: -0.1700
Data Index: 2661191 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7695. Min Range: -6.7695
Max Act: 6.6445. Min Act: -0.1700
Data Index: 6977401 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7695. Min Range: -6.7695
Max Act: 6.6132. Min Act: -0.1700
Data Index: 5553666 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7695. Min Range: -6.7695
Max Act: 6.6132. Min Act: -0.1700
Data Index: 892232 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7695. Min Range: -6.7695
Max Act: 6.6132. Min Act: -0.1700
Data Index: 5957068 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7695. Min Range: -6.7695
Max Act: 6.6132. Min Act: -0.1700
Data Index: 3779239 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7695. Min Range: -6.7695
Max Act: 6.5820. Min Act: -0.1700
Data Index: 3382438 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7695. Min Range: -6.7695
Max Act: 6.5507. Min Act: -0.1700
Data Index: 6211096 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7695. Min Range: -6.7695
Max Act: 6.5507. Min Act: -0.1700
Data Index: 8188472 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7695. Min Range: -6.7695
Max Act: 6.5195. Min Act: -0.1700
Data Index: 4699022 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7695. Min Range: -6.7695
Max Act: 6.5195. Min Act: -0.1700
Data Index: 4324201 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7695. Min Range: -6.7695
Max Act: 6.5195. Min Act: -0.1700
Data Index: 865651 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7695. Min Range: -6.7695
Max Act: 6.5195. Min Act: -0.1700
Data Index: 2538466 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7695. Min Range: -6.7695
Max Act: 6.4882. Min Act: -0.1700
Data Index: 2234585 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7695. Min Range: -6.7695
Max Act: 6.4570. Min Act: -0.1700
Data Index: 7760356 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7695. Min Range: -6.7695
Max Act: 6.4882. Min Act: -0.1700
Data Index: 3322666 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19