Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3811 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9872. Min Range: -8.9872
Max Act: 8.9872. Min Act: -0.1700
Data Index: 991853 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9872. Min Range: -8.9872
Max Act: 8.9247. Min Act: -0.1700
Data Index: 7874517 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9872. Min Range: -8.9872
Max Act: 8.6747. Min Act: -0.1700
Data Index: 4169000 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9872. Min Range: -8.9872
Max Act: 8.5497. Min Act: -0.1700
Data Index: 363584 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9872. Min Range: -8.9872
Max Act: 8.4872. Min Act: -0.1700
Data Index: 8818484 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9872. Min Range: -8.9872
Max Act: 8.4872. Min Act: -0.1700
Data Index: 2848840 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9872. Min Range: -8.9872
Max Act: 8.4872. Min Act: -0.1700
Data Index: 5537309 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9872. Min Range: -8.9872
Max Act: 8.4247. Min Act: -0.1700
Data Index: 4254828 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9872. Min Range: -8.9872
Max Act: 8.3622. Min Act: -0.1700
Data Index: 2585503 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9872. Min Range: -8.9872
Max Act: 8.3622. Min Act: -0.1700
Data Index: 5231193 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9872. Min Range: -8.9872
Max Act: 8.3622. Min Act: -0.1700
Data Index: 6384357 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9872. Min Range: -8.9872
Max Act: 8.3622. Min Act: -0.1700
Data Index: 7517391 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9872. Min Range: -8.9872
Max Act: 8.2997. Min Act: -0.1700
Data Index: 2621928 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9872. Min Range: -8.9872
Max Act: 8.3622. Min Act: -0.1700
Data Index: 1826194 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9872. Min Range: -8.9872
Max Act: 8.2997. Min Act: -0.1700
Data Index: 59383 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9872. Min Range: -8.9872
Max Act: 8.2372. Min Act: -0.1700
Data Index: 7201477 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9872. Min Range: -8.9872
Max Act: 8.2997. Min Act: -0.1700
Data Index: 2962668 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9872. Min Range: -8.9872
Max Act: 8.2372. Min Act: -0.1700
Data Index: 1816931 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9872. Min Range: -8.9872
Max Act: 8.2997. Min Act: -0.1700
Data Index: 8553135 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9872. Min Range: -8.9872
Max Act: 8.2372. Min Act: -0.1700
Data Index: 6719636 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19