Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4010 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4331. Min Range: -6.4331
Max Act: 6.4331. Min Act: -0.1700
Data Index: 2035262 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4331. Min Range: -6.4331
Max Act: 6.2143. Min Act: -0.1700
Data Index: 7782680 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4331. Min Range: -6.4331
Max Act: 6.2143. Min Act: -0.1700
Data Index: 7221299 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4331. Min Range: -6.4331
Max Act: 6.2143. Min Act: -0.1700
Data Index: 5742317 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4331. Min Range: -6.4331
Max Act: 6.0581. Min Act: -0.1700
Data Index: 8559761 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4331. Min Range: -6.4331
Max Act: 6.0268. Min Act: -0.1700
Data Index: 1057232 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4331. Min Range: -6.4331
Max Act: 5.9956. Min Act: -0.1700
Data Index: 7848347 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4331. Min Range: -6.4331
Max Act: 6.0268. Min Act: -0.1700
Data Index: 2045543 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4331. Min Range: -6.4331
Max Act: 6.0268. Min Act: -0.1700
Data Index: 1788555 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4331. Min Range: -6.4331
Max Act: 5.9643. Min Act: -0.1700
Data Index: 840825 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4331. Min Range: -6.4331
Max Act: 6.0268. Min Act: -0.1700
Data Index: 167129 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4331. Min Range: -6.4331
Max Act: 5.9643. Min Act: -0.1700
Data Index: 815755 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4331. Min Range: -6.4331
Max Act: 5.9956. Min Act: -0.1700
Data Index: 8210245 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4331. Min Range: -6.4331
Max Act: 5.9643. Min Act: -0.1700
Data Index: 3829058 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4331. Min Range: -6.4331
Max Act: 5.9643. Min Act: -0.1700
Data Index: 4851318 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4331. Min Range: -6.4331
Max Act: 5.9331. Min Act: -0.1700
Data Index: 459089 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4331. Min Range: -6.4331
Max Act: 5.9331. Min Act: -0.1700
Data Index: 802383 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4331. Min Range: -6.4331
Max Act: 5.9331. Min Act: -0.1700
Data Index: 3948308 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4331. Min Range: -6.4331
Max Act: 5.9643. Min Act: -0.1700
Data Index: 4672673 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4331. Min Range: -6.4331
Max Act: 5.8706. Min Act: -0.1700
Data Index: 4729208 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19