Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3473 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8828. Min Range: -7.8828
Max Act: 7.8828. Min Act: -0.1700
Data Index: 6794573 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8828. Min Range: -7.8828
Max Act: 7.8203. Min Act: -0.1700
Data Index: 5367706 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8828. Min Range: -7.8828
Max Act: 7.8203. Min Act: -0.1700
Data Index: 1131547 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8828. Min Range: -7.8828
Max Act: 7.7890. Min Act: -0.1700
Data Index: 5176431 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8828. Min Range: -7.8828
Max Act: 7.7265. Min Act: -0.1700
Data Index: 4479319 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8828. Min Range: -7.8828
Max Act: 7.7578. Min Act: -0.1700
Data Index: 5207204 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8828. Min Range: -7.8828
Max Act: 7.6953. Min Act: -0.1700
Data Index: 3082160 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8828. Min Range: -7.8828
Max Act: 7.6640. Min Act: -0.1700
Data Index: 3895948 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8828. Min Range: -7.8828
Max Act: 7.5703. Min Act: -0.1700
Data Index: 4558462 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8828. Min Range: -7.8828
Max Act: 7.5390. Min Act: -0.1700
Data Index: 5872639 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8828. Min Range: -7.8828
Max Act: 7.5078. Min Act: -0.1700
Data Index: 3214113 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8828. Min Range: -7.8828
Max Act: 7.4765. Min Act: -0.1700
Data Index: 4590665 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8828. Min Range: -7.8828
Max Act: 7.4765. Min Act: -0.1700
Data Index: 1527082 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8828. Min Range: -7.8828
Max Act: 7.4453. Min Act: -0.1700
Data Index: 7797798 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8828. Min Range: -7.8828
Max Act: 7.4453. Min Act: -0.1700
Data Index: 7635563 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8828. Min Range: -7.8828
Max Act: 7.4453. Min Act: -0.1700
Data Index: 6664159 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8828. Min Range: -7.8828
Max Act: 7.4140. Min Act: -0.1700
Data Index: 1403446 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8828. Min Range: -7.8828
Max Act: 7.3828. Min Act: -0.1700
Data Index: 5497408 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8828. Min Range: -7.8828
Max Act: 7.3828. Min Act: -0.1700
Data Index: 4578811 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8828. Min Range: -7.8828
Max Act: 7.3828. Min Act: -0.1700
Data Index: 3046908 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19