Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2705 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6758. Min Range: -5.6758
Max Act: 5.6758. Min Act: -0.1700
Data Index: 4817521 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6758. Min Range: -5.6758
Max Act: 5.6446. Min Act: -0.1700
Data Index: 8656094 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6758. Min Range: -5.6758
Max Act: 5.6446. Min Act: -0.1700
Data Index: 3451234 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6758. Min Range: -5.6758
Max Act: 5.6133. Min Act: -0.1700
Data Index: 2324395 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6758. Min Range: -5.6758
Max Act: 5.6446. Min Act: -0.1700
Data Index: 3102316 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6758. Min Range: -5.6758
Max Act: 5.5821. Min Act: -0.1700
Data Index: 5083776 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6758. Min Range: -5.6758
Max Act: 5.5821. Min Act: -0.1700
Data Index: 602262 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6758. Min Range: -5.6758
Max Act: 5.5821. Min Act: -0.1700
Data Index: 5739913 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6758. Min Range: -5.6758
Max Act: 5.5508. Min Act: -0.1700
Data Index: 7365414 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6758. Min Range: -5.6758
Max Act: 5.5821. Min Act: -0.1700
Data Index: 987644 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6758. Min Range: -5.6758
Max Act: 5.5508. Min Act: -0.1700
Data Index: 3134499 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6758. Min Range: -5.6758
Max Act: 5.5508. Min Act: -0.1700
Data Index: 2313199 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6758. Min Range: -5.6758
Max Act: 5.5508. Min Act: -0.1700
Data Index: 4988502 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6758. Min Range: -5.6758
Max Act: 5.5508. Min Act: -0.1700
Data Index: 4785156 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6758. Min Range: -5.6758
Max Act: 5.5508. Min Act: -0.1700
Data Index: 7365413 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6758. Min Range: -5.6758
Max Act: 5.5508. Min Act: -0.1700
Data Index: 3729007 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6758. Min Range: -5.6758
Max Act: 5.5196. Min Act: -0.1700
Data Index: 5966101 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6758. Min Range: -5.6758
Max Act: 5.5196. Min Act: -0.1700
Data Index: 4798186 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6758. Min Range: -5.6758
Max Act: 5.5196. Min Act: -0.1700
Data Index: 1703242 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6758. Min Range: -5.6758
Max Act: 5.5196. Min Act: -0.1700
Data Index: 1630866 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19