Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 324 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.7655. Min Act: -0.1700
Data Index: 3428585 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.4842. Min Act: -0.1700
Data Index: 716624 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.4842. Min Act: -0.1700
Data Index: 4220441 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.4217. Min Act: -0.1700
Data Index: 5856717 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.3905. Min Act: -0.1700
Data Index: 344529 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.3905. Min Act: -0.1700
Data Index: 2068348 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.2967. Min Act: -0.1700
Data Index: 6348191 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.3280. Min Act: -0.1700
Data Index: 261776 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.2655. Min Act: -0.1700
Data Index: 6095773 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.2967. Min Act: -0.1700
Data Index: 4102678 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.2342. Min Act: -0.1700
Data Index: 7957843 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.2342. Min Act: -0.1700
Data Index: 2298022 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.2342. Min Act: -0.1700
Data Index: 1597285 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.2029. Min Act: -0.1700
Data Index: 7948456 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.1717. Min Act: -0.1700
Data Index: 4023528 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.1717. Min Act: -0.1700
Data Index: 6305137 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.1717. Min Act: -0.1700
Data Index: 1091698 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.1404. Min Act: -0.1700
Data Index: 4242893 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.1404. Min Act: -0.1700
Data Index: 3083679 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.1404. Min Act: -0.1700
Data Index: 4618872 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19