Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1523 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5386. Min Range: -7.5386
Max Act: 7.5386. Min Act: -0.1700
Data Index: 4034921 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5386. Min Range: -7.5386
Max Act: 7.2574. Min Act: -0.1700
Data Index: 2384216 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5386. Min Range: -7.5386
Max Act: 7.2574. Min Act: -0.1700
Data Index: 2622995 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5386. Min Range: -7.5386
Max Act: 7.2261. Min Act: -0.1700
Data Index: 5922223 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5386. Min Range: -7.5386
Max Act: 7.2261. Min Act: -0.1700
Data Index: 2950369 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5386. Min Range: -7.5386
Max Act: 7.1949. Min Act: -0.1700
Data Index: 2770257 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5386. Min Range: -7.5386
Max Act: 7.1324. Min Act: -0.1700
Data Index: 508263 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5386. Min Range: -7.5386
Max Act: 7.1324. Min Act: -0.1700
Data Index: 1593083 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5386. Min Range: -7.5386
Max Act: 7.1011. Min Act: -0.1700
Data Index: 27560 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5386. Min Range: -7.5386
Max Act: 7.1324. Min Act: -0.1700
Data Index: 4182738 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5386. Min Range: -7.5386
Max Act: 7.1011. Min Act: -0.1700
Data Index: 5107559 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5386. Min Range: -7.5386
Max Act: 7.1011. Min Act: -0.1700
Data Index: 6276358 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5386. Min Range: -7.5386
Max Act: 7.0699. Min Act: -0.1700
Data Index: 759444 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5386. Min Range: -7.5386
Max Act: 7.0386. Min Act: -0.1700
Data Index: 1295724 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5386. Min Range: -7.5386
Max Act: 7.0074. Min Act: -0.1700
Data Index: 2014890 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5386. Min Range: -7.5386
Max Act: 7.0074. Min Act: -0.1700
Data Index: 870760 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5386. Min Range: -7.5386
Max Act: 7.0386. Min Act: -0.1700
Data Index: 5444553 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5386. Min Range: -7.5386
Max Act: 6.9761. Min Act: -0.1700
Data Index: 696412 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5386. Min Range: -7.5386
Max Act: 7.0074. Min Act: -0.1700
Data Index: 6111893 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5386. Min Range: -7.5386
Max Act: 6.9449. Min Act: -0.1700
Data Index: 6152703 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #19