Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4489 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3608. Min Range: -3.3608
Max Act: 3.3608. Min Act: -0.1700
Data Index: 2117069 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3608. Min Range: -3.3608
Max Act: 3.3294. Min Act: -0.1700
Data Index: 1291290 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3608. Min Range: -3.3608
Max Act: 3.3137. Min Act: -0.1700
Data Index: 1349387 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3608. Min Range: -3.3608
Max Act: 3.3294. Min Act: -0.1700
Data Index: 5070923 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3608. Min Range: -3.3608
Max Act: 3.3137. Min Act: -0.1700
Data Index: 771858 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3608. Min Range: -3.3608
Max Act: 3.2823. Min Act: -0.1700
Data Index: 658111 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3608. Min Range: -3.3608
Max Act: 3.2823. Min Act: -0.1700
Data Index: 6946721 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3608. Min Range: -3.3608
Max Act: 3.2823. Min Act: -0.1700
Data Index: 1965154 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3608. Min Range: -3.3608
Max Act: 3.2666. Min Act: -0.1700
Data Index: 6046513 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3608. Min Range: -3.3608
Max Act: 3.2666. Min Act: -0.1700
Data Index: 7143875 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3608. Min Range: -3.3608
Max Act: 3.2352. Min Act: -0.1700
Data Index: 7713296 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3608. Min Range: -3.3608
Max Act: 3.2666. Min Act: -0.1700
Data Index: 7183789 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3608. Min Range: -3.3608
Max Act: 3.2352. Min Act: -0.1700
Data Index: 1069009 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3608. Min Range: -3.3608
Max Act: 3.2195. Min Act: -0.1700
Data Index: 3069199 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3608. Min Range: -3.3608
Max Act: 3.2038. Min Act: -0.1700
Data Index: 6085613 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3608. Min Range: -3.3608
Max Act: 3.2038. Min Act: -0.1700
Data Index: 1093954 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3608. Min Range: -3.3608
Max Act: 3.2195. Min Act: -0.1700
Data Index: 3837031 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3608. Min Range: -3.3608
Max Act: 3.2038. Min Act: -0.1700
Data Index: 6059630 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3608. Min Range: -3.3608
Max Act: 3.2038. Min Act: -0.1700
Data Index: 2261121 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3608. Min Range: -3.3608
Max Act: 3.2038. Min Act: -0.1700
Data Index: 3376937 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19