Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5250 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3784. Min Range: -6.3784
Max Act: 6.3784. Min Act: -0.1700
Data Index: 8784627 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3784. Min Range: -6.3784
Max Act: 6.2534. Min Act: -0.1700
Data Index: 4077464 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3784. Min Range: -6.3784
Max Act: 6.2534. Min Act: -0.1700
Data Index: 7674183 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3784. Min Range: -6.3784
Max Act: 6.2534. Min Act: -0.1700
Data Index: 3435760 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3784. Min Range: -6.3784
Max Act: 6.1909. Min Act: -0.1700
Data Index: 3989189 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3784. Min Range: -6.3784
Max Act: 6.1909. Min Act: -0.1700
Data Index: 1552873 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3784. Min Range: -6.3784
Max Act: 6.1909. Min Act: -0.1700
Data Index: 6481833 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3784. Min Range: -6.3784
Max Act: 6.1909. Min Act: -0.1687
Data Index: 7759697 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3784. Min Range: -6.3784
Max Act: 6.1284. Min Act: -0.1700
Data Index: 5692038 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3784. Min Range: -6.3784
Max Act: 6.1284. Min Act: -0.1700
Data Index: 2795525 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3784. Min Range: -6.3784
Max Act: 6.1284. Min Act: -0.1700
Data Index: 533113 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3784. Min Range: -6.3784
Max Act: 6.1284. Min Act: -0.1700
Data Index: 6658954 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3784. Min Range: -6.3784
Max Act: 6.1284. Min Act: -0.1700
Data Index: 5366357 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3784. Min Range: -6.3784
Max Act: 6.0972. Min Act: -0.1700
Data Index: 3130698 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3784. Min Range: -6.3784
Max Act: 6.0972. Min Act: -0.1700
Data Index: 6658851 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3784. Min Range: -6.3784
Max Act: 6.0659. Min Act: -0.1700
Data Index: 3130696 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3784. Min Range: -6.3784
Max Act: 6.0659. Min Act: -0.1700
Data Index: 5582689 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3784. Min Range: -6.3784
Max Act: 6.0659. Min Act: -0.1700
Data Index: 14043 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3784. Min Range: -6.3784
Max Act: 6.0659. Min Act: -0.1700
Data Index: 7314900 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3784. Min Range: -6.3784
Max Act: 6.0659. Min Act: -0.1700
Data Index: 4305023 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19