Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5658 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7558. Min Range: -2.7558
Max Act: 2.7558. Min Act: -0.1700
Data Index: 5645727 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7558. Min Range: -2.7558
Max Act: 2.7239. Min Act: -0.1700
Data Index: 4492723 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7558. Min Range: -2.7558
Max Act: 2.6599. Min Act: -0.1700
Data Index: 538423 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7558. Min Range: -2.7558
Max Act: 2.6278. Min Act: -0.1700
Data Index: 74756 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7558. Min Range: -2.7558
Max Act: 2.6278. Min Act: -0.1700
Data Index: 7264823 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7558. Min Range: -2.7558
Max Act: 2.6117. Min Act: -0.1700
Data Index: 2035466 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7558. Min Range: -2.7558
Max Act: 2.5956. Min Act: -0.1700
Data Index: 5645726 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7558. Min Range: -2.7558
Max Act: 2.5795. Min Act: -0.1700
Data Index: 5819123 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7558. Min Range: -2.7558
Max Act: 2.5956. Min Act: -0.1700
Data Index: 4649057 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7558. Min Range: -2.7558
Max Act: 2.5795. Min Act: -0.1700
Data Index: 8201636 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7558. Min Range: -2.7558
Max Act: 2.5795. Min Act: -0.1700
Data Index: 4967480 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7558. Min Range: -2.7558
Max Act: 2.5795. Min Act: -0.1700
Data Index: 1564618 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7558. Min Range: -2.7558
Max Act: 2.4987. Min Act: -0.1700
Data Index: 4077369 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7558. Min Range: -2.7558
Max Act: 2.5149. Min Act: -0.1700
Data Index: 5005510 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7558. Min Range: -2.7558
Max Act: 2.4987. Min Act: -0.1700
Data Index: 3583364 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7558. Min Range: -2.7558
Max Act: 2.4662. Min Act: -0.1700
Data Index: 8538230 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7558. Min Range: -2.7558
Max Act: 2.4825. Min Act: -0.1700
Data Index: 7646722 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7558. Min Range: -2.7558
Max Act: 2.4662. Min Act: -0.1700
Data Index: 5645723 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7558. Min Range: -2.7558
Max Act: 2.4662. Min Act: -0.1700
Data Index: 350218 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7558. Min Range: -2.7558
Max Act: 2.4337. Min Act: -0.1700
Data Index: 251401 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19