Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5276 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0371. Min Range: -8.0371
Max Act: 8.0371. Min Act: -0.1700
Data Index: 1401540 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0371. Min Range: -8.0371
Max Act: 8.0371. Min Act: -0.1700
Data Index: 8464773 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0371. Min Range: -8.0371
Max Act: 7.9433. Min Act: -0.1700
Data Index: 7475742 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0371. Min Range: -8.0371
Max Act: 7.8808. Min Act: -0.1700
Data Index: 7796892 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0371. Min Range: -8.0371
Max Act: 7.8183. Min Act: -0.1700
Data Index: 5768554 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0371. Min Range: -8.0371
Max Act: 7.6933. Min Act: -0.1700
Data Index: 5010580 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0371. Min Range: -8.0371
Max Act: 7.6308. Min Act: -0.1700
Data Index: 2164967 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0371. Min Range: -8.0371
Max Act: 7.5996. Min Act: -0.1700
Data Index: 4293131 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0371. Min Range: -8.0371
Max Act: 7.5996. Min Act: -0.1700
Data Index: 7266215 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0371. Min Range: -8.0371
Max Act: 7.5683. Min Act: -0.1700
Data Index: 330455 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0371. Min Range: -8.0371
Max Act: 7.5371. Min Act: -0.1699
Data Index: 5905778 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0371. Min Range: -8.0371
Max Act: 7.4121. Min Act: -0.1700
Data Index: 4156110 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0371. Min Range: -8.0371
Max Act: 7.4433. Min Act: -0.1700
Data Index: 3674986 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0371. Min Range: -8.0371
Max Act: 7.3808. Min Act: -0.1700
Data Index: 6267466 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0371. Min Range: -8.0371
Max Act: 7.3183. Min Act: -0.1700
Data Index: 7612707 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0371. Min Range: -8.0371
Max Act: 7.1933. Min Act: -0.1700
Data Index: 5536094 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0371. Min Range: -8.0371
Max Act: 7.1933. Min Act: -0.1700
Data Index: 7078845 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0371. Min Range: -8.0371
Max Act: 7.1933. Min Act: -0.1700
Data Index: 331618 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0371. Min Range: -8.0371
Max Act: 7.0683. Min Act: -0.1700
Data Index: 3662060 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0371. Min Range: -8.0371
Max Act: 7.0371. Min Act: -0.1700
Data Index: 7575032 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19