Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 853 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4450. Min Range: -4.4450
Max Act: 4.4450. Min Act: -0.1700
Data Index: 7628372 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4450. Min Range: -4.4450
Max Act: 4.2262. Min Act: -0.1700
Data Index: 2974914 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4450. Min Range: -4.4450
Max Act: 4.1325. Min Act: -0.1700
Data Index: 6826941 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4450. Min Range: -4.4450
Max Act: 4.1325. Min Act: -0.1700
Data Index: 7947624 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4450. Min Range: -4.4450
Max Act: 4.1637. Min Act: -0.1700
Data Index: 2976475 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4450. Min Range: -4.4450
Max Act: 4.1637. Min Act: -0.1700
Data Index: 8270272 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4450. Min Range: -4.4450
Max Act: 4.1012. Min Act: -0.1700
Data Index: 4481399 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4450. Min Range: -4.4450
Max Act: 4.0700. Min Act: -0.1700
Data Index: 4669771 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4450. Min Range: -4.4450
Max Act: 4.0387. Min Act: -0.1700
Data Index: 628771 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4450. Min Range: -4.4450
Max Act: 4.0074. Min Act: -0.1700
Data Index: 2511859 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4450. Min Range: -4.4450
Max Act: 3.9762. Min Act: -0.1700
Data Index: 7113973 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4450. Min Range: -4.4450
Max Act: 3.9762. Min Act: -0.1700
Data Index: 143888 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4450. Min Range: -4.4450
Max Act: 4.0074. Min Act: -0.1700
Data Index: 2767612 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4450. Min Range: -4.4450
Max Act: 4.0074. Min Act: -0.1700
Data Index: 6836615 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4450. Min Range: -4.4450
Max Act: 3.9762. Min Act: -0.1700
Data Index: 2583748 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4450. Min Range: -4.4450
Max Act: 3.9762. Min Act: -0.1700
Data Index: 3437915 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4450. Min Range: -4.4450
Max Act: 3.9449. Min Act: -0.1700
Data Index: 4781340 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4450. Min Range: -4.4450
Max Act: 3.9762. Min Act: -0.1700
Data Index: 137854 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4450. Min Range: -4.4450
Max Act: 3.9449. Min Act: -0.1700
Data Index: 261579 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4450. Min Range: -4.4450
Max Act: 3.9449. Min Act: -0.1700
Data Index: 4077522 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19