Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3011 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6157. Min Range: -4.6157
Max Act: 4.6157. Min Act: -0.1700
Data Index: 1609626 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6157. Min Range: -4.6157
Max Act: 4.5844. Min Act: -0.1700
Data Index: 4389742 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6157. Min Range: -4.6157
Max Act: 4.4594. Min Act: -0.1700
Data Index: 4755730 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6157. Min Range: -4.6157
Max Act: 4.4282. Min Act: -0.1700
Data Index: 6573764 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6157. Min Range: -4.6157
Max Act: 4.2719. Min Act: -0.1700
Data Index: 620834 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6157. Min Range: -4.6157
Max Act: 4.2719. Min Act: -0.1700
Data Index: 8379415 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6157. Min Range: -4.6157
Max Act: 4.2719. Min Act: -0.1700
Data Index: 683481 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6157. Min Range: -4.6157
Max Act: 4.2407. Min Act: -0.1700
Data Index: 4898665 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6157. Min Range: -4.6157
Max Act: 4.2094. Min Act: -0.1700
Data Index: 5151546 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6157. Min Range: -4.6157
Max Act: 4.2407. Min Act: -0.1700
Data Index: 3243873 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6157. Min Range: -4.6157
Max Act: 4.2094. Min Act: -0.1700
Data Index: 4652891 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6157. Min Range: -4.6157
Max Act: 4.2094. Min Act: -0.1700
Data Index: 6607645 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6157. Min Range: -4.6157
Max Act: 4.2094. Min Act: -0.1700
Data Index: 7968825 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6157. Min Range: -4.6157
Max Act: 4.1782. Min Act: -0.1700
Data Index: 5047500 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6157. Min Range: -4.6157
Max Act: 4.1782. Min Act: -0.1700
Data Index: 374496 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6157. Min Range: -4.6157
Max Act: 4.1782. Min Act: -0.1700
Data Index: 4494985 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6157. Min Range: -4.6157
Max Act: 4.1469. Min Act: -0.1700
Data Index: 781647 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6157. Min Range: -4.6157
Max Act: 4.1469. Min Act: -0.1700
Data Index: 6362093 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6157. Min Range: -4.6157
Max Act: 4.1782. Min Act: -0.1700
Data Index: 5229684 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6157. Min Range: -4.6157
Max Act: 4.1469. Min Act: -0.1700
Data Index: 4505366 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19