Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1511 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.4874. Min Range: -0.4874
Max Act: 0.4874. Min Act: -0.1700
Data Index: 6090013 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4874. Min Range: -0.4874
Max Act: 0.4579. Min Act: -0.1699
Data Index: 1717515 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4874. Min Range: -0.4874
Max Act: 0.4433. Min Act: -0.1672
Data Index: 6571985 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4874. Min Range: -0.4874
Max Act: 0.4360. Min Act: -0.1700
Data Index: 7921351 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4874. Min Range: -0.4874
Max Act: 0.4145. Min Act: -0.1672
Data Index: 8362858 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4874. Min Range: -0.4874
Max Act: 0.4145. Min Act: -0.1700
Data Index: 589938 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4874. Min Range: -0.4874
Max Act: 0.4145. Min Act: -0.1672
Data Index: 4575769 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4874. Min Range: -0.4874
Max Act: 0.4073. Min Act: -0.1699
Data Index: 8196112 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4874. Min Range: -0.4874
Max Act: 0.4003. Min Act: -0.1698
Data Index: 2762296 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4874. Min Range: -0.4874
Max Act: 0.4003. Min Act: -0.1672
Data Index: 8142309 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4874. Min Range: -0.4874
Max Act: 0.3932. Min Act: -0.1672
Data Index: 4168792 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4874. Min Range: -0.4874
Max Act: 0.4003. Min Act: -0.1700
Data Index: 6709826 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4874. Min Range: -0.4874
Max Act: 0.3932. Min Act: -0.1700
Data Index: 3188617 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4874. Min Range: -0.4874
Max Act: 0.3932. Min Act: -0.1699
Data Index: 5118965 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4874. Min Range: -0.4874
Max Act: 0.3862. Min Act: -0.1699
Data Index: 1715403 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4874. Min Range: -0.4874
Max Act: 0.3862. Min Act: -0.1695
Data Index: 3059063 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4874. Min Range: -0.4874
Max Act: 0.3862. Min Act: -0.1698
Data Index: 1351814 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4874. Min Range: -0.4874
Max Act: 0.3792. Min Act: -0.1700
Data Index: 3015181 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4874. Min Range: -0.4874
Max Act: 0.3792. Min Act: -0.1694
Data Index: 3445986 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4874. Min Range: -0.4874
Max Act: 0.3862. Min Act: -0.1700
Data Index: 2500260 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #19