Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3446 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0481. Min Range: -8.0481
Max Act: 8.0481. Min Act: -0.1700
Data Index: 7470809 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0481. Min Range: -8.0481
Max Act: 7.7981. Min Act: -0.1700
Data Index: 8591037 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0481. Min Range: -8.0481
Max Act: 7.7356. Min Act: -0.1700
Data Index: 1456210 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0481. Min Range: -8.0481
Max Act: 7.6731. Min Act: -0.1700
Data Index: 2225265 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0481. Min Range: -8.0481
Max Act: 7.5481. Min Act: -0.1700
Data Index: 6749251 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0481. Min Range: -8.0481
Max Act: 7.5481. Min Act: -0.1700
Data Index: 6193784 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0481. Min Range: -8.0481
Max Act: 7.4856. Min Act: -0.1700
Data Index: 1318277 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0481. Min Range: -8.0481
Max Act: 7.4856. Min Act: -0.1700
Data Index: 5420178 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0481. Min Range: -8.0481
Max Act: 7.4856. Min Act: -0.1700
Data Index: 6058532 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0481. Min Range: -8.0481
Max Act: 7.4231. Min Act: -0.1700
Data Index: 1556263 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0481. Min Range: -8.0481
Max Act: 7.4231. Min Act: -0.1700
Data Index: 8137179 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0481. Min Range: -8.0481
Max Act: 7.3919. Min Act: -0.1700
Data Index: 3481888 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0481. Min Range: -8.0481
Max Act: 7.3606. Min Act: -0.1700
Data Index: 4512166 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0481. Min Range: -8.0481
Max Act: 7.3606. Min Act: -0.1700
Data Index: 1855720 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0481. Min Range: -8.0481
Max Act: 7.3294. Min Act: -0.1700
Data Index: 1185074 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0481. Min Range: -8.0481
Max Act: 7.2981. Min Act: -0.1700
Data Index: 8629816 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0481. Min Range: -8.0481
Max Act: 7.2669. Min Act: -0.1700
Data Index: 3342657 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0481. Min Range: -8.0481
Max Act: 7.2669. Min Act: -0.1700
Data Index: 5429668 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0481. Min Range: -8.0481
Max Act: 7.2981. Min Act: -0.1700
Data Index: 2013637 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0481. Min Range: -8.0481
Max Act: 7.2044. Min Act: -0.1700
Data Index: 1449702 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19