Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5114 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2037. Min Range: -6.2037
Max Act: 6.2037. Min Act: -0.1700
Data Index: 4061331 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.8287. Min Act: -0.1700
Data Index: 5676236 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.7349. Min Act: -0.1700
Data Index: 1296150 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.7662. Min Act: -0.1700
Data Index: 1359364 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.7037. Min Act: -0.1700
Data Index: 8000012 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.7037. Min Act: -0.1700
Data Index: 1663432 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.6412. Min Act: -0.1700
Data Index: 851955 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.6099. Min Act: -0.1700
Data Index: 8248762 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.5787. Min Act: -0.1700
Data Index: 5790148 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.5474. Min Act: -0.1700
Data Index: 8613202 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.5162. Min Act: -0.1700
Data Index: 8562732 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.4537. Min Act: -0.1700
Data Index: 5092871 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.4537. Min Act: -0.1700
Data Index: 8563791 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.4224. Min Act: -0.1700
Data Index: 5050731 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.4224. Min Act: -0.1700
Data Index: 6121443 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.3912. Min Act: -0.1700
Data Index: 2938458 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.3912. Min Act: -0.1700
Data Index: 15297 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.3912. Min Act: -0.1700
Data Index: 890115 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.3599. Min Act: -0.1700
Data Index: 5146363 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.3599. Min Act: -0.1700
Data Index: 1998203 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19