Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2005 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5404. Min Range: -4.5404
Max Act: 4.5404. Min Act: -0.1700
Data Index: 1045305 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5404. Min Range: -4.5404
Max Act: 4.5404. Min Act: -0.1700
Data Index: 8557554 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5404. Min Range: -4.5404
Max Act: 4.3841. Min Act: -0.1700
Data Index: 7953861 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5404. Min Range: -4.5404
Max Act: 4.3841. Min Act: -0.1700
Data Index: 1945320 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5404. Min Range: -4.5404
Max Act: 4.4154. Min Act: -0.1700
Data Index: 55487 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5404. Min Range: -4.5404
Max Act: 4.3529. Min Act: -0.1700
Data Index: 5615020 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5404. Min Range: -4.5404
Max Act: 4.3841. Min Act: -0.1700
Data Index: 6470000 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5404. Min Range: -4.5404
Max Act: 4.3216. Min Act: -0.1700
Data Index: 1221397 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5404. Min Range: -4.5404
Max Act: 4.3529. Min Act: -0.1700
Data Index: 2963248 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5404. Min Range: -4.5404
Max Act: 4.3216. Min Act: -0.1700
Data Index: 4138592 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5404. Min Range: -4.5404
Max Act: 4.3529. Min Act: -0.1700
Data Index: 2388997 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5404. Min Range: -4.5404
Max Act: 4.3841. Min Act: -0.1700
Data Index: 6321287 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5404. Min Range: -4.5404
Max Act: 4.3529. Min Act: -0.1700
Data Index: 8010969 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5404. Min Range: -4.5404
Max Act: 4.3529. Min Act: -0.1700
Data Index: 8009903 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5404. Min Range: -4.5404
Max Act: 4.3529. Min Act: -0.1700
Data Index: 3702880 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5404. Min Range: -4.5404
Max Act: 4.3216. Min Act: -0.1700
Data Index: 7775390 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5404. Min Range: -4.5404
Max Act: 4.3216. Min Act: -0.1700
Data Index: 6263225 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5404. Min Range: -4.5404
Max Act: 4.3216. Min Act: -0.1700
Data Index: 8690804 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5404. Min Range: -4.5404
Max Act: 4.3529. Min Act: -0.1700
Data Index: 7953868 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5404. Min Range: -4.5404
Max Act: 4.3216. Min Act: -0.1700
Data Index: 4085047 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19