Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1577 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0366. Min Range: -5.0366
Max Act: 5.0366. Min Act: -0.1700
Data Index: 3915781 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.9741. Min Act: -0.1700
Data Index: 6436594 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.9428. Min Act: -0.1700
Data Index: 8178025 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.9428. Min Act: -0.1698
Data Index: 4817207 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.8491. Min Act: -0.1700
Data Index: 6121157 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.8491. Min Act: -0.1700
Data Index: 6189467 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.8178. Min Act: -0.1700
Data Index: 3045100 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.8178. Min Act: -0.1700
Data Index: 6623094 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.8178. Min Act: -0.1700
Data Index: 752632 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.7866. Min Act: -0.1700
Data Index: 5324555 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.7866. Min Act: -0.1700
Data Index: 610184 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.7866. Min Act: -0.1700
Data Index: 3535388 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.7866. Min Act: -0.1700
Data Index: 1531435 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.7553. Min Act: -0.1700
Data Index: 3236359 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.7553. Min Act: -0.1700
Data Index: 7046531 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.7553. Min Act: -0.1700
Data Index: 5043189 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.7241. Min Act: -0.1700
Data Index: 2207616 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.7241. Min Act: -0.1700
Data Index: 6298928 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.7241. Min Act: -0.1700
Data Index: 6460981 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0366. Min Range: -5.0366
Max Act: 4.6928. Min Act: -0.1700
Data Index: 6118582 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19