Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 48 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7048. Min Range: -9.7048
Max Act: 9.7048. Min Act: -0.1700
Data Index: 3247963 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7048. Min Range: -9.7048
Max Act: 9.4548. Min Act: -0.1700
Data Index: 3310328 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7048. Min Range: -9.7048
Max Act: 8.8923. Min Act: -0.1700
Data Index: 3797398 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7048. Min Range: -9.7048
Max Act: 8.7673. Min Act: -0.1700
Data Index: 5810739 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7048. Min Range: -9.7048
Max Act: 8.6423. Min Act: -0.1700
Data Index: 7990049 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7048. Min Range: -9.7048
Max Act: 8.6423. Min Act: -0.1700
Data Index: 2829285 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7048. Min Range: -9.7048
Max Act: 8.5798. Min Act: -0.1700
Data Index: 1595965 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7048. Min Range: -9.7048
Max Act: 8.5798. Min Act: -0.1700
Data Index: 345190 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7048. Min Range: -9.7048
Max Act: 8.5173. Min Act: -0.1700
Data Index: 2644605 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7048. Min Range: -9.7048
Max Act: 8.5173. Min Act: -0.1700
Data Index: 6183288 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7048. Min Range: -9.7048
Max Act: 8.5173. Min Act: -0.1700
Data Index: 7251340 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7048. Min Range: -9.7048
Max Act: 8.5173. Min Act: -0.1700
Data Index: 1248792 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7048. Min Range: -9.7048
Max Act: 8.5173. Min Act: -0.1700
Data Index: 8729409 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7048. Min Range: -9.7048
Max Act: 8.4548. Min Act: -0.1700
Data Index: 8559958 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7048. Min Range: -9.7048
Max Act: 8.4548. Min Act: -0.1700
Data Index: 2509795 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7048. Min Range: -9.7048
Max Act: 8.4548. Min Act: -0.1700
Data Index: 3572840 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7048. Min Range: -9.7048
Max Act: 8.4548. Min Act: -0.1700
Data Index: 1424055 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7048. Min Range: -9.7048
Max Act: 8.4548. Min Act: -0.1700
Data Index: 7698964 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7048. Min Range: -9.7048
Max Act: 8.3923. Min Act: -0.1700
Data Index: 3774531 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7048. Min Range: -9.7048
Max Act: 8.3923. Min Act: -0.1700
Data Index: 4889650 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #19