Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1598 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4876. Min Range: -5.4876
Max Act: 5.4876. Min Act: -0.1700
Data Index: 3423794 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4876. Min Range: -5.4876
Max Act: 5.2689. Min Act: -0.1700
Data Index: 3007043 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4876. Min Range: -5.4876
Max Act: 5.2376. Min Act: -0.1700
Data Index: 3199502 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4876. Min Range: -5.4876
Max Act: 5.1751. Min Act: -0.1700
Data Index: 2512866 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4876. Min Range: -5.4876
Max Act: 5.0814. Min Act: -0.1700
Data Index: 488017 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4876. Min Range: -5.4876
Max Act: 5.0189. Min Act: -0.1700
Data Index: 3667084 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4876. Min Range: -5.4876
Max Act: 5.0189. Min Act: -0.1700
Data Index: 2245011 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4876. Min Range: -5.4876
Max Act: 4.9251. Min Act: -0.1700
Data Index: 8332150 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4876. Min Range: -5.4876
Max Act: 4.8001. Min Act: -0.1700
Data Index: 5575154 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4876. Min Range: -5.4876
Max Act: 4.9876. Min Act: -0.1700
Data Index: 6277623 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4876. Min Range: -5.4876
Max Act: 4.9876. Min Act: -0.1700
Data Index: 662907 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4876. Min Range: -5.4876
Max Act: 4.9251. Min Act: -0.1700
Data Index: 7009862 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4876. Min Range: -5.4876
Max Act: 4.8626. Min Act: -0.1700
Data Index: 2467368 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4876. Min Range: -5.4876
Max Act: 4.8939. Min Act: -0.1700
Data Index: 932766 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4876. Min Range: -5.4876
Max Act: 4.8626. Min Act: -0.1700
Data Index: 7993380 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4876. Min Range: -5.4876
Max Act: 4.8626. Min Act: -0.1700
Data Index: 6028889 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4876. Min Range: -5.4876
Max Act: 4.9564. Min Act: -0.1700
Data Index: 8705054 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4876. Min Range: -5.4876
Max Act: 4.8939. Min Act: -0.1700
Data Index: 6533885 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4876. Min Range: -5.4876
Max Act: 4.8001. Min Act: -0.1700
Data Index: 4871129 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4876. Min Range: -5.4876
Max Act: 4.8939. Min Act: -0.1700
Data Index: 3730799 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19