Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2386 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7961. Min Range: -3.7961
Max Act: 3.7961. Min Act: -0.1700
Data Index: 5039592 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7961. Min Range: -3.7961
Max Act: 3.7492. Min Act: -0.1700
Data Index: 6196779 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7961. Min Range: -3.7961
Max Act: 3.7649. Min Act: -0.1700
Data Index: 3838384 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7961. Min Range: -3.7961
Max Act: 3.7179. Min Act: -0.1700
Data Index: 7835876 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7961. Min Range: -3.7961
Max Act: 3.7336. Min Act: -0.1700
Data Index: 822323 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7961. Min Range: -3.7961
Max Act: 3.7179. Min Act: -0.1700
Data Index: 3301187 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7961. Min Range: -3.7961
Max Act: 3.7023. Min Act: -0.1700
Data Index: 1846584 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7961. Min Range: -3.7961
Max Act: 3.7023. Min Act: -0.1700
Data Index: 7766115 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7961. Min Range: -3.7961
Max Act: 3.6866. Min Act: -0.1700
Data Index: 3077333 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7961. Min Range: -3.7961
Max Act: 3.6866. Min Act: -0.1700
Data Index: 5223088 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7961. Min Range: -3.7961
Max Act: 3.6710. Min Act: -0.1700
Data Index: 540325 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7961. Min Range: -3.7961
Max Act: 3.6710. Min Act: -0.1700
Data Index: 1461176 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7961. Min Range: -3.7961
Max Act: 3.6554. Min Act: -0.1700
Data Index: 579879 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7961. Min Range: -3.7961
Max Act: 3.6397. Min Act: -0.1700
Data Index: 1424062 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7961. Min Range: -3.7961
Max Act: 3.6397. Min Act: -0.1700
Data Index: 4715758 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7961. Min Range: -3.7961
Max Act: 3.6397. Min Act: -0.1700
Data Index: 6138426 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7961. Min Range: -3.7961
Max Act: 3.6084. Min Act: -0.1700
Data Index: 5987679 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7961. Min Range: -3.7961
Max Act: 3.6084. Min Act: -0.1700
Data Index: 1026635 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7961. Min Range: -3.7961
Max Act: 3.6084. Min Act: -0.1700
Data Index: 6315927 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7961. Min Range: -3.7961
Max Act: 3.5771. Min Act: -0.1700
Data Index: 2600641 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19