Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 891 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2479. Min Range: -4.2479
Max Act: 4.2479. Min Act: -0.1700
Data Index: 6890680 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2479. Min Range: -4.2479
Max Act: 4.2167. Min Act: -0.1700
Data Index: 6458821 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2479. Min Range: -4.2479
Max Act: 4.2167. Min Act: -0.1700
Data Index: 8804418 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2479. Min Range: -4.2479
Max Act: 4.1854. Min Act: -0.1700
Data Index: 4716860 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2479. Min Range: -4.2479
Max Act: 4.1542. Min Act: -0.1700
Data Index: 2135635 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2479. Min Range: -4.2479
Max Act: 4.1542. Min Act: -0.1700
Data Index: 8719783 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2479. Min Range: -4.2479
Max Act: 4.1229. Min Act: -0.1700
Data Index: 1853612 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2479. Min Range: -4.2479
Max Act: 4.1229. Min Act: -0.1700
Data Index: 4516444 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2479. Min Range: -4.2479
Max Act: 4.1229. Min Act: -0.1700
Data Index: 4978522 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2479. Min Range: -4.2479
Max Act: 4.0917. Min Act: -0.1700
Data Index: 2905254 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2479. Min Range: -4.2479
Max Act: 4.0917. Min Act: -0.1700
Data Index: 7233347 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2479. Min Range: -4.2479
Max Act: 4.0292. Min Act: -0.1700
Data Index: 6922017 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2479. Min Range: -4.2479
Max Act: 4.0604. Min Act: -0.1700
Data Index: 4656026 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2479. Min Range: -4.2479
Max Act: 4.0917. Min Act: -0.1700
Data Index: 8418609 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2479. Min Range: -4.2479
Max Act: 3.9979. Min Act: -0.1700
Data Index: 2932390 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2479. Min Range: -4.2479
Max Act: 3.9666. Min Act: -0.1700
Data Index: 2888356 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2479. Min Range: -4.2479
Max Act: 3.9979. Min Act: -0.1700
Data Index: 404599 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2479. Min Range: -4.2479
Max Act: 3.9979. Min Act: -0.1700
Data Index: 772410 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2479. Min Range: -4.2479
Max Act: 3.9666. Min Act: -0.1700
Data Index: 1250383 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2479. Min Range: -4.2479
Max Act: 3.9666. Min Act: -0.1700
Data Index: 2135643 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19