Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3573 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6694. Min Range: -4.6694
Max Act: 4.6694. Min Act: -0.1700
Data Index: 8565963 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6694. Min Range: -4.6694
Max Act: 4.5756. Min Act: -0.1700
Data Index: 27196 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6694. Min Range: -4.6694
Max Act: 4.5756. Min Act: -0.1700
Data Index: 6997566 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6694. Min Range: -4.6694
Max Act: 4.5444. Min Act: -0.1700
Data Index: 4624914 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6694. Min Range: -4.6694
Max Act: 4.4819. Min Act: -0.1700
Data Index: 3786399 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6694. Min Range: -4.6694
Max Act: 4.4819. Min Act: -0.1700
Data Index: 4964183 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6694. Min Range: -4.6694
Max Act: 4.4819. Min Act: -0.1700
Data Index: 6693077 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6694. Min Range: -4.6694
Max Act: 4.4506. Min Act: -0.1700
Data Index: 1199078 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6694. Min Range: -4.6694
Max Act: 4.4506. Min Act: -0.1700
Data Index: 708156 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6694. Min Range: -4.6694
Max Act: 4.4194. Min Act: -0.1700
Data Index: 6289501 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6694. Min Range: -4.6694
Max Act: 4.3569. Min Act: -0.1700
Data Index: 1089985 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6694. Min Range: -4.6694
Max Act: 4.3569. Min Act: -0.1700
Data Index: 708157 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6694. Min Range: -4.6694
Max Act: 4.3569. Min Act: -0.1700
Data Index: 2261539 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6694. Min Range: -4.6694
Max Act: 4.3256. Min Act: -0.1700
Data Index: 2269076 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6694. Min Range: -4.6694
Max Act: 4.2631. Min Act: -0.1700
Data Index: 2582973 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6694. Min Range: -4.6694
Max Act: 4.2318. Min Act: -0.1700
Data Index: 6911951 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6694. Min Range: -4.6694
Max Act: 4.2318. Min Act: -0.1700
Data Index: 3044301 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6694. Min Range: -4.6694
Max Act: 4.2631. Min Act: -0.1700
Data Index: 2257605 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6694. Min Range: -4.6694
Max Act: 4.2318. Min Act: -0.1700
Data Index: 4928340 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6694. Min Range: -4.6694
Max Act: 4.2318. Min Act: -0.1700
Data Index: 2491106 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19