Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3065 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9761. Min Range: -5.9761
Max Act: 5.9761. Min Act: -0.1700
Data Index: 1840358 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9761. Min Range: -5.9761
Max Act: 5.9136. Min Act: -0.1700
Data Index: 2210157 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9761. Min Range: -5.9761
Max Act: 5.9136. Min Act: -0.1700
Data Index: 3465626 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9761. Min Range: -5.9761
Max Act: 5.8824. Min Act: -0.1700
Data Index: 2150821 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9761. Min Range: -5.9761
Max Act: 5.8824. Min Act: -0.1700
Data Index: 8223207 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9761. Min Range: -5.9761
Max Act: 5.8511. Min Act: -0.1700
Data Index: 8745137 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9761. Min Range: -5.9761
Max Act: 5.7574. Min Act: -0.1700
Data Index: 5972097 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9761. Min Range: -5.9761
Max Act: 5.7574. Min Act: -0.1700
Data Index: 6836230 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9761. Min Range: -5.9761
Max Act: 5.7261. Min Act: -0.1700
Data Index: 1000299 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9761. Min Range: -5.9761
Max Act: 5.7574. Min Act: -0.1700
Data Index: 8815536 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9761. Min Range: -5.9761
Max Act: 5.6949. Min Act: -0.1700
Data Index: 2760474 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9761. Min Range: -5.9761
Max Act: 5.6949. Min Act: -0.1700
Data Index: 5081035 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9761. Min Range: -5.9761
Max Act: 5.6636. Min Act: -0.1700
Data Index: 4822302 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9761. Min Range: -5.9761
Max Act: 5.7261. Min Act: -0.1700
Data Index: 6476602 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9761. Min Range: -5.9761
Max Act: 5.6949. Min Act: -0.1700
Data Index: 2089620 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9761. Min Range: -5.9761
Max Act: 5.6636. Min Act: -0.1700
Data Index: 7606778 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9761. Min Range: -5.9761
Max Act: 5.6949. Min Act: -0.1700
Data Index: 1750240 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9761. Min Range: -5.9761
Max Act: 5.6636. Min Act: -0.1700
Data Index: 4300140 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9761. Min Range: -5.9761
Max Act: 5.6011. Min Act: -0.1700
Data Index: 1411218 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9761. Min Range: -5.9761
Max Act: 5.6324. Min Act: -0.1700
Data Index: 7111500 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19