Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1022 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8035. Min Range: -3.8035
Max Act: 3.8035. Min Act: -0.1700
Data Index: 2308999 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8035. Min Range: -3.8035
Max Act: 3.8035. Min Act: -0.1700
Data Index: 8640445 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8035. Min Range: -3.8035
Max Act: 3.6470. Min Act: -0.1700
Data Index: 4205849 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8035. Min Range: -3.8035
Max Act: 3.6470. Min Act: -0.1700
Data Index: 1019803 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8035. Min Range: -3.8035
Max Act: 3.6470. Min Act: -0.1700
Data Index: 570751 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8035. Min Range: -3.8035
Max Act: 3.6314. Min Act: -0.1700
Data Index: 570759 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8035. Min Range: -3.8035
Max Act: 3.6001. Min Act: -0.1700
Data Index: 7430898 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8035. Min Range: -3.8035
Max Act: 3.5688. Min Act: -0.1700
Data Index: 7556900 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8035. Min Range: -3.8035
Max Act: 3.5062. Min Act: -0.1700
Data Index: 8081967 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8035. Min Range: -3.8035
Max Act: 3.5062. Min Act: -0.1700
Data Index: 3270495 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8035. Min Range: -3.8035
Max Act: 3.5218. Min Act: -0.1700
Data Index: 6333582 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8035. Min Range: -3.8035
Max Act: 3.5218. Min Act: -0.1700
Data Index: 2418404 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8035. Min Range: -3.8035
Max Act: 3.5062. Min Act: -0.1700
Data Index: 817085 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8035. Min Range: -3.8035
Max Act: 3.4905. Min Act: -0.1700
Data Index: 775723 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8035. Min Range: -3.8035
Max Act: 3.4592. Min Act: -0.1700
Data Index: 40113 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8035. Min Range: -3.8035
Max Act: 3.4592. Min Act: -0.1700
Data Index: 5609325 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8035. Min Range: -3.8035
Max Act: 3.4748. Min Act: -0.1700
Data Index: 970606 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8035. Min Range: -3.8035
Max Act: 3.4435. Min Act: -0.1700
Data Index: 3325240 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8035. Min Range: -3.8035
Max Act: 3.4435. Min Act: -0.1700
Data Index: 2491582 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8035. Min Range: -3.8035
Max Act: 3.4435. Min Act: -0.1700
Data Index: 3566425 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19