Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3149 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.9899. Min Act: -0.1700
Data Index: 3719921 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.9274. Min Act: -0.1700
Data Index: 3835766 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.8649. Min Act: -0.1700
Data Index: 6601514 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.7712. Min Act: -0.1700
Data Index: 6619858 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.7712. Min Act: -0.1700
Data Index: 4591670 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.7399. Min Act: -0.1700
Data Index: 2496243 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.7399. Min Act: -0.1700
Data Index: 4058073 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.7399. Min Act: -0.1700
Data Index: 2268579 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.7087. Min Act: -0.1700
Data Index: 4313941 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.7087. Min Act: -0.1700
Data Index: 6162216 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.6774. Min Act: -0.1700
Data Index: 8053581 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.7087. Min Act: -0.1700
Data Index: 8428684 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.6774. Min Act: -0.1700
Data Index: 744401 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.6774. Min Act: -0.1700
Data Index: 8595247 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.6462. Min Act: -0.1700
Data Index: 2416803 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.6149. Min Act: -0.1700
Data Index: 4150582 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.6149. Min Act: -0.1700
Data Index: 2631636 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.5837. Min Act: -0.1700
Data Index: 6068723 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.5837. Min Act: -0.1700
Data Index: 5245466 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.5837. Min Act: -0.1700
Data Index: 3660580 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19