Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3563 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.3553. Min Act: -0.1700
Data Index: 6670992 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.3389. Min Act: -0.1700
Data Index: 7060825 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.3389. Min Act: -0.1700
Data Index: 4331458 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.2896. Min Act: -0.1700
Data Index: 729825 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.3389. Min Act: -0.1700
Data Index: 6087133 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.3061. Min Act: -0.1700
Data Index: 5527522 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.2731. Min Act: -0.1700
Data Index: 6706443 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.2896. Min Act: -0.1700
Data Index: 2220458 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.2236. Min Act: -0.1700
Data Index: 6654757 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.2401. Min Act: -0.1700
Data Index: 8762264 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.2401. Min Act: -0.1700
Data Index: 561700 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.2401. Min Act: -0.1700
Data Index: 3181968 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.2236. Min Act: -0.1700
Data Index: 6375954 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.2070. Min Act: -0.1700
Data Index: 3901721 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.2236. Min Act: -0.1700
Data Index: 7478213 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.2070. Min Act: -0.1700
Data Index: 7079142 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.2070. Min Act: -0.1700
Data Index: 2415563 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.2566. Min Act: -0.1700
Data Index: 1111107 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.2401. Min Act: -0.1700
Data Index: 5676111 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.2236. Min Act: -0.1700
Data Index: 124032 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19