Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2658 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3714. Min Range: -6.3714
Max Act: 6.3714. Min Act: -0.1700
Data Index: 3659716 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3714. Min Range: -6.3714
Max Act: 6.2777. Min Act: -0.1700
Data Index: 7968175 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3714. Min Range: -6.3714
Max Act: 6.1527. Min Act: -0.1700
Data Index: 8357235 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3714. Min Range: -6.3714
Max Act: 6.1527. Min Act: -0.1700
Data Index: 7578913 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3714. Min Range: -6.3714
Max Act: 6.0589. Min Act: -0.1700
Data Index: 7073608 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3714. Min Range: -6.3714
Max Act: 5.9964. Min Act: -0.1700
Data Index: 4503362 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3714. Min Range: -6.3714
Max Act: 5.9964. Min Act: -0.1700
Data Index: 7876530 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3714. Min Range: -6.3714
Max Act: 5.9652. Min Act: -0.1700
Data Index: 7351965 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3714. Min Range: -6.3714
Max Act: 5.9339. Min Act: -0.1700
Data Index: 6214582 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3714. Min Range: -6.3714
Max Act: 5.9339. Min Act: -0.1700
Data Index: 4067222 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3714. Min Range: -6.3714
Max Act: 5.9339. Min Act: -0.1700
Data Index: 1057428 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3714. Min Range: -6.3714
Max Act: 5.9339. Min Act: -0.1700
Data Index: 7876538 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3714. Min Range: -6.3714
Max Act: 5.9339. Min Act: -0.1700
Data Index: 4617265 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3714. Min Range: -6.3714
Max Act: 5.9339. Min Act: -0.1700
Data Index: 4253602 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3714. Min Range: -6.3714
Max Act: 5.8714. Min Act: -0.1700
Data Index: 7770787 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3714. Min Range: -6.3714
Max Act: 5.8402. Min Act: -0.1700
Data Index: 7730380 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3714. Min Range: -6.3714
Max Act: 5.8402. Min Act: -0.1700
Data Index: 5224524 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3714. Min Range: -6.3714
Max Act: 5.8089. Min Act: -0.1700
Data Index: 6363864 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3714. Min Range: -6.3714
Max Act: 5.8089. Min Act: -0.1700
Data Index: 586999 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3714. Min Range: -6.3714
Max Act: 5.8402. Min Act: -0.1700
Data Index: 7453032 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #19