Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3636 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3977. Min Range: -7.3977
Max Act: 7.3977. Min Act: -0.1700
Data Index: 1179362 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3977. Min Range: -7.3977
Max Act: 7.2102. Min Act: -0.1700
Data Index: 7150441 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3977. Min Range: -7.3977
Max Act: 7.1477. Min Act: -0.1700
Data Index: 6723110 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3977. Min Range: -7.3977
Max Act: 7.1477. Min Act: -0.1700
Data Index: 4813432 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3977. Min Range: -7.3977
Max Act: 7.0852. Min Act: -0.1700
Data Index: 4324334 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3977. Min Range: -7.3977
Max Act: 7.0852. Min Act: -0.1700
Data Index: 4339435 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3977. Min Range: -7.3977
Max Act: 7.0540. Min Act: -0.1700
Data Index: 2717478 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3977. Min Range: -7.3977
Max Act: 7.0227. Min Act: -0.1700
Data Index: 3198206 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3977. Min Range: -7.3977
Max Act: 7.0227. Min Act: -0.1700
Data Index: 990711 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3977. Min Range: -7.3977
Max Act: 6.9915. Min Act: -0.1700
Data Index: 6730763 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3977. Min Range: -7.3977
Max Act: 6.9915. Min Act: -0.1700
Data Index: 4098674 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3977. Min Range: -7.3977
Max Act: 6.9602. Min Act: -0.1700
Data Index: 7434260 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3977. Min Range: -7.3977
Max Act: 6.9290. Min Act: -0.1700
Data Index: 6995352 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3977. Min Range: -7.3977
Max Act: 6.9602. Min Act: -0.1700
Data Index: 2714266 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3977. Min Range: -7.3977
Max Act: 6.8977. Min Act: -0.1700
Data Index: 3017431 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3977. Min Range: -7.3977
Max Act: 6.8977. Min Act: -0.1700
Data Index: 8008349 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3977. Min Range: -7.3977
Max Act: 6.8977. Min Act: -0.1700
Data Index: 7631179 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3977. Min Range: -7.3977
Max Act: 6.8977. Min Act: -0.1700
Data Index: 2929312 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3977. Min Range: -7.3977
Max Act: 6.8665. Min Act: -0.1700
Data Index: 775692 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3977. Min Range: -7.3977
Max Act: 6.8977. Min Act: -0.1700
Data Index: 4935855 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19