Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3720 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5507. Min Range: -3.5507
Max Act: 3.5507. Min Act: -0.1700
Data Index: 2146285 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5507. Min Range: -3.5507
Max Act: 3.4724. Min Act: -0.1700
Data Index: 5268600 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5507. Min Range: -3.5507
Max Act: 3.4097. Min Act: -0.1700
Data Index: 946750 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5507. Min Range: -3.5507
Max Act: 3.3940. Min Act: -0.1700
Data Index: 6838406 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5507. Min Range: -3.5507
Max Act: 3.3940. Min Act: -0.1700
Data Index: 3788330 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5507. Min Range: -3.5507
Max Act: 3.3783. Min Act: -0.1700
Data Index: 511824 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5507. Min Range: -3.5507
Max Act: 3.3470. Min Act: -0.1700
Data Index: 7044049 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5507. Min Range: -3.5507
Max Act: 3.3313. Min Act: -0.1700
Data Index: 4559539 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5507. Min Range: -3.5507
Max Act: 3.3156. Min Act: -0.1700
Data Index: 3325611 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5507. Min Range: -3.5507
Max Act: 3.3156. Min Act: -0.1700
Data Index: 4991043 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5507. Min Range: -3.5507
Max Act: 3.3156. Min Act: -0.1700
Data Index: 2846415 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5507. Min Range: -3.5507
Max Act: 3.3313. Min Act: -0.1700
Data Index: 2280630 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5507. Min Range: -3.5507
Max Act: 3.3313. Min Act: -0.1700
Data Index: 6351988 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5507. Min Range: -3.5507
Max Act: 3.3156. Min Act: -0.1700
Data Index: 2072926 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5507. Min Range: -3.5507
Max Act: 3.2999. Min Act: -0.1700
Data Index: 8059495 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5507. Min Range: -3.5507
Max Act: 3.2999. Min Act: -0.1700
Data Index: 5606570 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5507. Min Range: -3.5507
Max Act: 3.2842. Min Act: -0.1700
Data Index: 8059494 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5507. Min Range: -3.5507
Max Act: 3.2842. Min Act: -0.1700
Data Index: 5312074 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5507. Min Range: -3.5507
Max Act: 3.2999. Min Act: -0.1700
Data Index: 4546694 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5507. Min Range: -3.5507
Max Act: 3.2685. Min Act: -0.1700
Data Index: 1078095 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19