Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2998 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 20.2247. Min Range: -20.2247
Max Act: 20.2247. Min Act: -0.1700
Data Index: 4686892 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 20.2247. Min Range: -20.2247
Max Act: 19.9747. Min Act: -0.1700
Data Index: 641446 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 20.2247. Min Range: -20.2247
Max Act: 19.9747. Min Act: -0.1700
Data Index: 1688697 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 20.2247. Min Range: -20.2247
Max Act: 19.8497. Min Act: -0.1700
Data Index: 7506261 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 20.2247. Min Range: -20.2247
Max Act: 19.8497. Min Act: -0.1700
Data Index: 7260242 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 20.2247. Min Range: -20.2247
Max Act: 19.7247. Min Act: -0.1700
Data Index: 1773120 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 20.2247. Min Range: -20.2247
Max Act: 19.7247. Min Act: -0.1700
Data Index: 4904955 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 20.2247. Min Range: -20.2247
Max Act: 19.5997. Min Act: -0.1700
Data Index: 5225949 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 20.2247. Min Range: -20.2247
Max Act: 19.4747. Min Act: -0.1700
Data Index: 7084678 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 20.2247. Min Range: -20.2247
Max Act: 19.4747. Min Act: -0.1700
Data Index: 420384 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 20.2247. Min Range: -20.2247
Max Act: 19.4747. Min Act: -0.1700
Data Index: 2410960 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 20.2247. Min Range: -20.2247
Max Act: 19.3497. Min Act: -0.1700
Data Index: 7764836 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 20.2247. Min Range: -20.2247
Max Act: 19.4747. Min Act: -0.1700
Data Index: 8678655 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 20.2247. Min Range: -20.2247
Max Act: 19.4747. Min Act: -0.1700
Data Index: 2131698 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 20.2247. Min Range: -20.2247
Max Act: 19.3497. Min Act: -0.1700
Data Index: 6194937 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 20.2247. Min Range: -20.2247
Max Act: 19.3497. Min Act: -0.1700
Data Index: 4052717 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 20.2247. Min Range: -20.2247
Max Act: 19.3497. Min Act: -0.1700
Data Index: 1626644 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 20.2247. Min Range: -20.2247
Max Act: 19.3497. Min Act: -0.1700
Data Index: 6932365 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 20.2247. Min Range: -20.2247
Max Act: 19.3497. Min Act: -0.1700
Data Index: 2399521 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 20.2247. Min Range: -20.2247
Max Act: 19.2247. Min Act: -0.1700
Data Index: 2748579 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #19