Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4184 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6224. Min Range: -4.6224
Max Act: 4.6224. Min Act: -0.1700
Data Index: 2119215 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6224. Min Range: -4.6224
Max Act: 4.4974. Min Act: -0.1700
Data Index: 6375982 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6224. Min Range: -4.6224
Max Act: 4.4037. Min Act: -0.1700
Data Index: 1354319 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6224. Min Range: -4.6224
Max Act: 4.3099. Min Act: -0.1700
Data Index: 5095168 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6224. Min Range: -4.6224
Max Act: 4.3099. Min Act: -0.1700
Data Index: 5272954 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6224. Min Range: -4.6224
Max Act: 4.3099. Min Act: -0.1700
Data Index: 7199084 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6224. Min Range: -4.6224
Max Act: 4.2786. Min Act: -0.1700
Data Index: 8483142 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6224. Min Range: -4.6224
Max Act: 4.2786. Min Act: -0.1700
Data Index: 3319796 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6224. Min Range: -4.6224
Max Act: 4.2474. Min Act: -0.1700
Data Index: 2119214 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6224. Min Range: -4.6224
Max Act: 4.2474. Min Act: -0.1700
Data Index: 5464026 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6224. Min Range: -4.6224
Max Act: 4.2474. Min Act: -0.1700
Data Index: 34594 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6224. Min Range: -4.6224
Max Act: 4.1849. Min Act: -0.1700
Data Index: 5656900 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6224. Min Range: -4.6224
Max Act: 4.1536. Min Act: -0.1700
Data Index: 8283907 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6224. Min Range: -4.6224
Max Act: 4.1536. Min Act: -0.1700
Data Index: 1948673 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6224. Min Range: -4.6224
Max Act: 4.1536. Min Act: -0.1700
Data Index: 2694765 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6224. Min Range: -4.6224
Max Act: 4.1224. Min Act: -0.1700
Data Index: 2557139 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6224. Min Range: -4.6224
Max Act: 4.1224. Min Act: -0.1700
Data Index: 4814166 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6224. Min Range: -4.6224
Max Act: 4.1224. Min Act: -0.1700
Data Index: 2739880 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6224. Min Range: -4.6224
Max Act: 4.1224. Min Act: -0.1700
Data Index: 1885526 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6224. Min Range: -4.6224
Max Act: 4.1224. Min Act: -0.1700
Data Index: 7218573 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19