Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3196 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.9597. Min Act: -0.1700
Data Index: 3250323 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.7409. Min Act: -0.1700
Data Index: 7007903 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.7409. Min Act: -0.1700
Data Index: 6712246 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.7097. Min Act: -0.1700
Data Index: 2106122 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.6784. Min Act: -0.1700
Data Index: 4663938 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.6784. Min Act: -0.1700
Data Index: 656433 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.6784. Min Act: -0.1700
Data Index: 8233561 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.6159. Min Act: -0.1700
Data Index: 376098 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.5847. Min Act: -0.1700
Data Index: 6025737 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.5534. Min Act: -0.1700
Data Index: 4314060 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.5222. Min Act: -0.1700
Data Index: 1552425 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.4909. Min Act: -0.1700
Data Index: 4333985 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.5222. Min Act: -0.1700
Data Index: 3131737 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.4909. Min Act: -0.1700
Data Index: 8830371 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.4597. Min Act: -0.1700
Data Index: 921452 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.4909. Min Act: -0.1700
Data Index: 3013280 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.4284. Min Act: -0.1700
Data Index: 6255665 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.4284. Min Act: -0.1700
Data Index: 3433943 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.4284. Min Act: -0.1700
Data Index: 7938725 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.3659. Min Act: -0.1700
Data Index: 5791916 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19