Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5393 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7620. Min Range: -6.7620
Max Act: 6.7620. Min Act: -0.1700
Data Index: 2714878 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7620. Min Range: -6.7620
Max Act: 6.7307. Min Act: -0.1700
Data Index: 3551787 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7620. Min Range: -6.7620
Max Act: 6.6057. Min Act: -0.1700
Data Index: 4508868 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7620. Min Range: -6.7620
Max Act: 6.5745. Min Act: -0.1700
Data Index: 3375633 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7620. Min Range: -6.7620
Max Act: 6.5120. Min Act: -0.1700
Data Index: 5282118 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7620. Min Range: -6.7620
Max Act: 6.4807. Min Act: -0.1700
Data Index: 363816 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7620. Min Range: -6.7620
Max Act: 6.4495. Min Act: -0.1700
Data Index: 2408142 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7620. Min Range: -6.7620
Max Act: 6.4495. Min Act: -0.1700
Data Index: 1437923 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7620. Min Range: -6.7620
Max Act: 6.4182. Min Act: -0.1699
Data Index: 8580865 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7620. Min Range: -6.7620
Max Act: 6.3870. Min Act: -0.1700
Data Index: 147742 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7620. Min Range: -6.7620
Max Act: 6.4182. Min Act: -0.1700
Data Index: 287782 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7620. Min Range: -6.7620
Max Act: 6.4182. Min Act: -0.1700
Data Index: 3055265 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7620. Min Range: -6.7620
Max Act: 6.3557. Min Act: -0.1700
Data Index: 2482020 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7620. Min Range: -6.7620
Max Act: 6.3245. Min Act: -0.1700
Data Index: 2638572 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7620. Min Range: -6.7620
Max Act: 6.3245. Min Act: -0.1700
Data Index: 7673675 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7620. Min Range: -6.7620
Max Act: 6.2932. Min Act: -0.1700
Data Index: 7331929 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7620. Min Range: -6.7620
Max Act: 6.3245. Min Act: -0.1700
Data Index: 2000087 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7620. Min Range: -6.7620
Max Act: 6.2932. Min Act: -0.1700
Data Index: 1067314 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7620. Min Range: -6.7620
Max Act: 6.2932. Min Act: -0.1700
Data Index: 5099966 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7620. Min Range: -6.7620
Max Act: 6.2932. Min Act: -0.1700
Data Index: 4675091 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19