Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3576 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8053. Min Range: -6.8053
Max Act: 6.8053. Min Act: -0.1700
Data Index: 3510389 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8053. Min Range: -6.8053
Max Act: 6.8053. Min Act: -0.1700
Data Index: 6031537 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8053. Min Range: -6.8053
Max Act: 6.8053. Min Act: -0.1700
Data Index: 8327381 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8053. Min Range: -6.8053
Max Act: 6.7740. Min Act: -0.1700
Data Index: 4917548 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8053. Min Range: -6.8053
Max Act: 6.7740. Min Act: -0.1700
Data Index: 7819278 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8053. Min Range: -6.8053
Max Act: 6.7428. Min Act: -0.1700
Data Index: 8176540 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8053. Min Range: -6.8053
Max Act: 6.7428. Min Act: -0.1700
Data Index: 7155483 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8053. Min Range: -6.8053
Max Act: 6.7115. Min Act: -0.1700
Data Index: 1530056 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8053. Min Range: -6.8053
Max Act: 6.6490. Min Act: -0.1700
Data Index: 2969812 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8053. Min Range: -6.8053
Max Act: 6.6490. Min Act: -0.1700
Data Index: 7548626 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8053. Min Range: -6.8053
Max Act: 6.6178. Min Act: -0.1700
Data Index: 2496805 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8053. Min Range: -6.8053
Max Act: 6.6178. Min Act: -0.1700
Data Index: 1627080 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8053. Min Range: -6.8053
Max Act: 6.6490. Min Act: -0.1700
Data Index: 999117 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8053. Min Range: -6.8053
Max Act: 6.6178. Min Act: -0.1700
Data Index: 5358420 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8053. Min Range: -6.8053
Max Act: 6.6178. Min Act: -0.1700
Data Index: 7533713 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8053. Min Range: -6.8053
Max Act: 6.6178. Min Act: -0.1700
Data Index: 4295891 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8053. Min Range: -6.8053
Max Act: 6.5865. Min Act: -0.1700
Data Index: 4496182 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8053. Min Range: -6.8053
Max Act: 6.5865. Min Act: -0.1700
Data Index: 5841755 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8053. Min Range: -6.8053
Max Act: 6.5865. Min Act: -0.1700
Data Index: 6448531 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8053. Min Range: -6.8053
Max Act: 6.5865. Min Act: -0.1700
Data Index: 2847993 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19