Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 47 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1010. Min Range: -6.1010
Max Act: 6.1010. Min Act: -0.1700
Data Index: 7065393 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1010. Min Range: -6.1010
Max Act: 6.0698. Min Act: -0.1700
Data Index: 26011 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1010. Min Range: -6.1010
Max Act: 6.0698. Min Act: -0.1700
Data Index: 770462 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1010. Min Range: -6.1010
Max Act: 5.9760. Min Act: -0.1700
Data Index: 770459 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1010. Min Range: -6.1010
Max Act: 5.8823. Min Act: -0.1700
Data Index: 6070160 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1010. Min Range: -6.1010
Max Act: 5.8823. Min Act: -0.1700
Data Index: 3189828 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1010. Min Range: -6.1010
Max Act: 5.7260. Min Act: -0.1700
Data Index: 5982917 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1010. Min Range: -6.1010
Max Act: 5.7260. Min Act: -0.1700
Data Index: 2838088 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1010. Min Range: -6.1010
Max Act: 5.6948. Min Act: -0.1700
Data Index: 7823961 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1010. Min Range: -6.1010
Max Act: 5.7260. Min Act: -0.1700
Data Index: 241982 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1010. Min Range: -6.1010
Max Act: 5.6948. Min Act: -0.1700
Data Index: 4197568 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1010. Min Range: -6.1010
Max Act: 5.6635. Min Act: -0.1700
Data Index: 8779102 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1010. Min Range: -6.1010
Max Act: 5.6323. Min Act: -0.1700
Data Index: 2537904 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1010. Min Range: -6.1010
Max Act: 5.6323. Min Act: -0.1700
Data Index: 5705315 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1010. Min Range: -6.1010
Max Act: 5.6323. Min Act: -0.1700
Data Index: 7635363 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1010. Min Range: -6.1010
Max Act: 5.6323. Min Act: -0.1700
Data Index: 8083263 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1010. Min Range: -6.1010
Max Act: 5.6323. Min Act: -0.1700
Data Index: 35671 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1010. Min Range: -6.1010
Max Act: 5.6323. Min Act: -0.1700
Data Index: 7405942 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1010. Min Range: -6.1010
Max Act: 5.6323. Min Act: -0.1700
Data Index: 1231421 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1010. Min Range: -6.1010
Max Act: 5.6010. Min Act: -0.1700
Data Index: 6861513 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #19