Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3294 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8397. Min Range: -5.8397
Max Act: 5.8397. Min Act: -0.1700
Data Index: 2724207 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8397. Min Range: -5.8397
Max Act: 5.7772. Min Act: -0.1700
Data Index: 2365762 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8397. Min Range: -5.8397
Max Act: 5.6835. Min Act: -0.1700
Data Index: 3846466 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8397. Min Range: -5.8397
Max Act: 5.6522. Min Act: -0.1700
Data Index: 3938706 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8397. Min Range: -5.8397
Max Act: 5.6522. Min Act: -0.1700
Data Index: 3333698 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8397. Min Range: -5.8397
Max Act: 5.5897. Min Act: -0.1700
Data Index: 2880324 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8397. Min Range: -5.8397
Max Act: 5.5585. Min Act: -0.1700
Data Index: 1593926 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8397. Min Range: -5.8397
Max Act: 5.5585. Min Act: -0.1700
Data Index: 7453417 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8397. Min Range: -5.8397
Max Act: 5.5585. Min Act: -0.1700
Data Index: 2174811 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8397. Min Range: -5.8397
Max Act: 5.5585. Min Act: -0.1700
Data Index: 2225930 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8397. Min Range: -5.8397
Max Act: 5.5272. Min Act: -0.1700
Data Index: 3257419 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8397. Min Range: -5.8397
Max Act: 5.4960. Min Act: -0.1700
Data Index: 2107638 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8397. Min Range: -5.8397
Max Act: 5.5272. Min Act: -0.1700
Data Index: 6897062 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8397. Min Range: -5.8397
Max Act: 5.5272. Min Act: -0.1700
Data Index: 6689104 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8397. Min Range: -5.8397
Max Act: 5.5272. Min Act: -0.1700
Data Index: 8650718 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8397. Min Range: -5.8397
Max Act: 5.5272. Min Act: -0.1699
Data Index: 8569682 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8397. Min Range: -5.8397
Max Act: 5.5585. Min Act: -0.1699
Data Index: 5676760 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8397. Min Range: -5.8397
Max Act: 5.5272. Min Act: -0.1700
Data Index: 7120597 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8397. Min Range: -5.8397
Max Act: 5.4960. Min Act: -0.1700
Data Index: 5384660 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8397. Min Range: -5.8397
Max Act: 5.4960. Min Act: -0.1700
Data Index: 1552279 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19