Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3534 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2541. Min Range: -5.2541
Max Act: 5.2541. Min Act: -0.1700
Data Index: 6429412 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2541. Min Range: -5.2541
Max Act: 5.2228. Min Act: -0.1700
Data Index: 1063315 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2541. Min Range: -5.2541
Max Act: 5.2228. Min Act: -0.1700
Data Index: 448170 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2541. Min Range: -5.2541
Max Act: 5.1916. Min Act: -0.1700
Data Index: 908964 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2541. Min Range: -5.2541
Max Act: 5.1916. Min Act: -0.1700
Data Index: 3458566 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2541. Min Range: -5.2541
Max Act: 5.1603. Min Act: -0.1700
Data Index: 5265808 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2541. Min Range: -5.2541
Max Act: 5.1603. Min Act: -0.1700
Data Index: 448422 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2541. Min Range: -5.2541
Max Act: 5.1603. Min Act: -0.1700
Data Index: 7073103 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2541. Min Range: -5.2541
Max Act: 5.1603. Min Act: -0.1700
Data Index: 6937304 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2541. Min Range: -5.2541
Max Act: 5.1291. Min Act: -0.1700
Data Index: 8766176 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2541. Min Range: -5.2541
Max Act: 5.0666. Min Act: -0.1700
Data Index: 1819532 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2541. Min Range: -5.2541
Max Act: 5.0666. Min Act: -0.1700
Data Index: 5579627 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2541. Min Range: -5.2541
Max Act: 5.0666. Min Act: -0.1700
Data Index: 5299324 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2541. Min Range: -5.2541
Max Act: 5.0666. Min Act: -0.1700
Data Index: 6656164 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2541. Min Range: -5.2541
Max Act: 5.0041. Min Act: -0.1700
Data Index: 3709888 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2541. Min Range: -5.2541
Max Act: 4.9728. Min Act: -0.1700
Data Index: 5461094 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2541. Min Range: -5.2541
Max Act: 4.9728. Min Act: -0.1700
Data Index: 2455522 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2541. Min Range: -5.2541
Max Act: 4.9416. Min Act: -0.1700
Data Index: 519686 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2541. Min Range: -5.2541
Max Act: 4.9416. Min Act: -0.1700
Data Index: 7314199 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2541. Min Range: -5.2541
Max Act: 4.9103. Min Act: -0.1700
Data Index: 588592 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19