Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3546 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3301. Min Range: -5.3301
Max Act: 5.3301. Min Act: -0.1700
Data Index: 4926140 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3301. Min Range: -5.3301
Max Act: 5.3301. Min Act: -0.1700
Data Index: 7455098 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3301. Min Range: -5.3301
Max Act: 5.2364. Min Act: -0.1700
Data Index: 5077671 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3301. Min Range: -5.3301
Max Act: 5.2364. Min Act: -0.1700
Data Index: 4064547 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3301. Min Range: -5.3301
Max Act: 5.2051. Min Act: -0.1700
Data Index: 5010468 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3301. Min Range: -5.3301
Max Act: 5.2051. Min Act: -0.1700
Data Index: 6814432 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3301. Min Range: -5.3301
Max Act: 5.2051. Min Act: -0.1700
Data Index: 6380649 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3301. Min Range: -5.3301
Max Act: 5.1426. Min Act: -0.1700
Data Index: 1581749 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3301. Min Range: -5.3301
Max Act: 5.1426. Min Act: -0.1700
Data Index: 441700 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3301. Min Range: -5.3301
Max Act: 5.1114. Min Act: -0.1700
Data Index: 3495281 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3301. Min Range: -5.3301
Max Act: 5.0801. Min Act: -0.1700
Data Index: 1445870 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3301. Min Range: -5.3301
Max Act: 5.0801. Min Act: -0.1700
Data Index: 7058712 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3301. Min Range: -5.3301
Max Act: 5.0801. Min Act: -0.1700
Data Index: 6677548 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3301. Min Range: -5.3301
Max Act: 5.0801. Min Act: -0.1700
Data Index: 5300976 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3301. Min Range: -5.3301
Max Act: 5.0801. Min Act: -0.1700
Data Index: 1479825 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3301. Min Range: -5.3301
Max Act: 5.0801. Min Act: -0.1700
Data Index: 7962281 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3301. Min Range: -5.3301
Max Act: 5.0801. Min Act: -0.1700
Data Index: 670996 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3301. Min Range: -5.3301
Max Act: 5.0489. Min Act: -0.1700
Data Index: 4903860 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3301. Min Range: -5.3301
Max Act: 5.0489. Min Act: -0.1700
Data Index: 752493 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3301. Min Range: -5.3301
Max Act: 5.0489. Min Act: -0.1700
Data Index: 7797506 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19