Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4653 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7793. Min Range: -4.7793
Max Act: 4.7793. Min Act: -0.1700
Data Index: 468672 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7793. Min Range: -4.7793
Max Act: 4.7793. Min Act: -0.1700
Data Index: 6891047 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7793. Min Range: -4.7793
Max Act: 4.6855. Min Act: -0.1700
Data Index: 3588485 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7793. Min Range: -4.7793
Max Act: 4.6855. Min Act: -0.1700
Data Index: 5102312 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7793. Min Range: -4.7793
Max Act: 4.6855. Min Act: -0.1700
Data Index: 2382729 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7793. Min Range: -4.7793
Max Act: 4.6855. Min Act: -0.1700
Data Index: 7317584 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7793. Min Range: -4.7793
Max Act: 4.6543. Min Act: -0.1700
Data Index: 7773850 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7793. Min Range: -4.7793
Max Act: 4.6543. Min Act: -0.1700
Data Index: 5640047 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7793. Min Range: -4.7793
Max Act: 4.6543. Min Act: -0.1700
Data Index: 4071807 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7793. Min Range: -4.7793
Max Act: 4.6543. Min Act: -0.1700
Data Index: 8561901 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7793. Min Range: -4.7793
Max Act: 4.6543. Min Act: -0.1700
Data Index: 5607330 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7793. Min Range: -4.7793
Max Act: 4.6543. Min Act: -0.1700
Data Index: 2694447 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7793. Min Range: -4.7793
Max Act: 4.5918. Min Act: -0.1700
Data Index: 2199790 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7793. Min Range: -4.7793
Max Act: 4.6230. Min Act: -0.1700
Data Index: 7436734 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7793. Min Range: -4.7793
Max Act: 4.6230. Min Act: -0.1700
Data Index: 7791860 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7793. Min Range: -4.7793
Max Act: 4.5918. Min Act: -0.1700
Data Index: 5789654 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7793. Min Range: -4.7793
Max Act: 4.6230. Min Act: -0.1700
Data Index: 3810363 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7793. Min Range: -4.7793
Max Act: 4.5918. Min Act: -0.1700
Data Index: 4371694 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7793. Min Range: -4.7793
Max Act: 4.5918. Min Act: -0.1700
Data Index: 1159155 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7793. Min Range: -4.7793
Max Act: 4.5918. Min Act: -0.1700
Data Index: 5640048 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #19