Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2261 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3769. Min Range: -5.3769
Max Act: 5.3769. Min Act: -0.1700
Data Index: 3548386 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3769. Min Range: -5.3769
Max Act: 5.3769. Min Act: -0.1700
Data Index: 6401803 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3769. Min Range: -5.3769
Max Act: 5.3769. Min Act: -0.1700
Data Index: 1100712 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3769. Min Range: -5.3769
Max Act: 5.3769. Min Act: -0.1700
Data Index: 1739932 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3769. Min Range: -5.3769
Max Act: 5.3769. Min Act: -0.1700
Data Index: 2952559 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3769. Min Range: -5.3769
Max Act: 5.3456. Min Act: -0.1700
Data Index: 7640107 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3769. Min Range: -5.3769
Max Act: 5.3144. Min Act: -0.1700
Data Index: 8441465 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3769. Min Range: -5.3769
Max Act: 5.2831. Min Act: -0.1700
Data Index: 6722081 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3769. Min Range: -5.3769
Max Act: 5.2831. Min Act: -0.1700
Data Index: 4172817 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3769. Min Range: -5.3769
Max Act: 5.2519. Min Act: -0.1700
Data Index: 5708749 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3769. Min Range: -5.3769
Max Act: 5.2519. Min Act: -0.1700
Data Index: 6236334 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3769. Min Range: -5.3769
Max Act: 5.2519. Min Act: -0.1700
Data Index: 6572180 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3769. Min Range: -5.3769
Max Act: 5.2206. Min Act: -0.1700
Data Index: 8772522 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3769. Min Range: -5.3769
Max Act: 5.2519. Min Act: -0.1700
Data Index: 7396329 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3769. Min Range: -5.3769
Max Act: 5.2519. Min Act: -0.1700
Data Index: 3825293 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3769. Min Range: -5.3769
Max Act: 5.2519. Min Act: -0.1700
Data Index: 7210235 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3769. Min Range: -5.3769
Max Act: 5.2206. Min Act: -0.1700
Data Index: 6627415 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3769. Min Range: -5.3769
Max Act: 5.2206. Min Act: -0.1700
Data Index: 6332658 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3769. Min Range: -5.3769
Max Act: 5.2206. Min Act: -0.1700
Data Index: 7042679 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3769. Min Range: -5.3769
Max Act: 5.1894. Min Act: -0.1700
Data Index: 5467643 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19