Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1776 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0300. Min Range: -9.0300
Max Act: 9.0300. Min Act: -0.1700
Data Index: 6163800 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0300. Min Range: -9.0300
Max Act: 8.8425. Min Act: -0.1700
Data Index: 6163789 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0300. Min Range: -9.0300
Max Act: 8.1862. Min Act: -0.1700
Data Index: 7173174 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0300. Min Range: -9.0300
Max Act: 8.1550. Min Act: -0.1700
Data Index: 5045587 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0300. Min Range: -9.0300
Max Act: 8.1550. Min Act: -0.1700
Data Index: 5694990 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0300. Min Range: -9.0300
Max Act: 8.1550. Min Act: -0.1700
Data Index: 1577003 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0300. Min Range: -9.0300
Max Act: 8.1550. Min Act: -0.1700
Data Index: 6366440 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0300. Min Range: -9.0300
Max Act: 8.1237. Min Act: -0.1700
Data Index: 4619600 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0300. Min Range: -9.0300
Max Act: 8.1237. Min Act: -0.1700
Data Index: 4321696 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0300. Min Range: -9.0300
Max Act: 8.1237. Min Act: -0.1700
Data Index: 8176071 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0300. Min Range: -9.0300
Max Act: 8.1237. Min Act: -0.1700
Data Index: 3410782 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0300. Min Range: -9.0300
Max Act: 8.0925. Min Act: -0.1700
Data Index: 6869000 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0300. Min Range: -9.0300
Max Act: 8.0300. Min Act: -0.1700
Data Index: 8447847 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0300. Min Range: -9.0300
Max Act: 8.0612. Min Act: -0.1700
Data Index: 4668695 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0300. Min Range: -9.0300
Max Act: 8.0300. Min Act: -0.1700
Data Index: 6143983 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0300. Min Range: -9.0300
Max Act: 8.0612. Min Act: -0.1700
Data Index: 7698121 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0300. Min Range: -9.0300
Max Act: 8.0300. Min Act: -0.1700
Data Index: 3013315 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0300. Min Range: -9.0300
Max Act: 8.0300. Min Act: -0.1700
Data Index: 7514853 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0300. Min Range: -9.0300
Max Act: 8.0300. Min Act: -0.1700
Data Index: 768409 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0300. Min Range: -9.0300
Max Act: 7.9987. Min Act: -0.1700
Data Index: 2963090 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #19