Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2404 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7797. Min Range: -2.7797
Max Act: 2.7797. Min Act: -0.1700
Data Index: 1716159 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7797. Min Range: -2.7797
Max Act: 2.7478. Min Act: -0.1700
Data Index: 8483261 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7797. Min Range: -2.7797
Max Act: 2.7318. Min Act: -0.1700
Data Index: 3402211 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7797. Min Range: -2.7797
Max Act: 2.7318. Min Act: -0.1700
Data Index: 4406328 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7797. Min Range: -2.7797
Max Act: 2.7318. Min Act: -0.1700
Data Index: 5472406 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7797. Min Range: -2.7797
Max Act: 2.7318. Min Act: -0.1700
Data Index: 7849121 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7797. Min Range: -2.7797
Max Act: 2.6999. Min Act: -0.1700
Data Index: 3578040 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7797. Min Range: -2.7797
Max Act: 2.6838. Min Act: -0.1700
Data Index: 6812869 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7797. Min Range: -2.7797
Max Act: 2.6678. Min Act: -0.1700
Data Index: 7618111 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7797. Min Range: -2.7797
Max Act: 2.6518. Min Act: -0.1700
Data Index: 7349974 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7797. Min Range: -2.7797
Max Act: 2.6678. Min Act: -0.1700
Data Index: 6127554 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7797. Min Range: -2.7797
Max Act: 2.6678. Min Act: -0.1700
Data Index: 1177450 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7797. Min Range: -2.7797
Max Act: 2.6518. Min Act: -0.1700
Data Index: 3578039 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7797. Min Range: -2.7797
Max Act: 2.6357. Min Act: -0.1700
Data Index: 6464058 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7797. Min Range: -2.7797
Max Act: 2.6357. Min Act: -0.1700
Data Index: 6551289 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7797. Min Range: -2.7797
Max Act: 2.6357. Min Act: -0.1700
Data Index: 5472407 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7797. Min Range: -2.7797
Max Act: 2.6357. Min Act: -0.1700
Data Index: 1668008 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7797. Min Range: -2.7797
Max Act: 2.6197. Min Act: -0.1700
Data Index: 690993 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7797. Min Range: -2.7797
Max Act: 2.6036. Min Act: -0.1700
Data Index: 5227679 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7797. Min Range: -2.7797
Max Act: 2.6197. Min Act: -0.1700
Data Index: 5452535 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19