Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 906 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.4248. Min Act: -0.1700
Data Index: 1563850 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.3310. Min Act: -0.1700
Data Index: 4419696 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.3310. Min Act: -0.1700
Data Index: 2777704 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.2685. Min Act: -0.1700
Data Index: 196892 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.2372. Min Act: -0.1700
Data Index: 5894067 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.2060. Min Act: -0.1700
Data Index: 7322335 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.1747. Min Act: -0.1700
Data Index: 5251515 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.1747. Min Act: -0.1700
Data Index: 6319203 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.1747. Min Act: -0.1700
Data Index: 8549045 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.1747. Min Act: -0.1700
Data Index: 8801654 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.1435. Min Act: -0.1700
Data Index: 718159 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.1435. Min Act: -0.1700
Data Index: 3176387 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.1122. Min Act: -0.1700
Data Index: 4239645 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.1435. Min Act: -0.1700
Data Index: 4206888 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.1122. Min Act: -0.1700
Data Index: 5914700 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.0810. Min Act: -0.1700
Data Index: 5972572 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.0810. Min Act: -0.1700
Data Index: 1860429 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.0810. Min Act: -0.1700
Data Index: 5914701 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.0810. Min Act: -0.1700
Data Index: 2069953 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.0810. Min Act: -0.1700
Data Index: 1757922 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #19