Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3032 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7863. Min Range: -3.7863
Max Act: 3.7863. Min Act: -0.1700
Data Index: 5781010 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7863. Min Range: -3.7863
Max Act: 3.7394. Min Act: -0.1700
Data Index: 4985866 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7863. Min Range: -3.7863
Max Act: 3.7394. Min Act: -0.1700
Data Index: 8210961 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7863. Min Range: -3.7863
Max Act: 3.7394. Min Act: -0.1700
Data Index: 5198617 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7863. Min Range: -3.7863
Max Act: 3.6769. Min Act: -0.1700
Data Index: 1983258 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7863. Min Range: -3.7863
Max Act: 3.6612. Min Act: -0.1700
Data Index: 6510322 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7863. Min Range: -3.7863
Max Act: 3.6456. Min Act: -0.1700
Data Index: 8648593 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7863. Min Range: -3.7863
Max Act: 3.6612. Min Act: -0.1700
Data Index: 4475522 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7863. Min Range: -3.7863
Max Act: 3.6143. Min Act: -0.1700
Data Index: 5571545 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7863. Min Range: -3.7863
Max Act: 3.6143. Min Act: -0.1700
Data Index: 5256264 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7863. Min Range: -3.7863
Max Act: 3.6143. Min Act: -0.1700
Data Index: 2549190 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7863. Min Range: -3.7863
Max Act: 3.6299. Min Act: -0.1700
Data Index: 605507 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7863. Min Range: -3.7863
Max Act: 3.5986. Min Act: -0.1700
Data Index: 4730510 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7863. Min Range: -3.7863
Max Act: 3.6143. Min Act: -0.1700
Data Index: 3892357 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7863. Min Range: -3.7863
Max Act: 3.5986. Min Act: -0.1700
Data Index: 1094801 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7863. Min Range: -3.7863
Max Act: 3.5986. Min Act: -0.1700
Data Index: 8480074 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7863. Min Range: -3.7863
Max Act: 3.5830. Min Act: -0.1700
Data Index: 7231945 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7863. Min Range: -3.7863
Max Act: 3.5986. Min Act: -0.1700
Data Index: 4031744 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7863. Min Range: -3.7863
Max Act: 3.5830. Min Act: -0.1700
Data Index: 591683 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7863. Min Range: -3.7863
Max Act: 3.5673. Min Act: -0.1700
Data Index: 8359275 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19