Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1058 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4440. Min Range: -6.4440
Max Act: 6.4440. Min Act: -0.1700
Data Index: 6375021 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4440. Min Range: -6.4440
Max Act: 6.0690. Min Act: -0.1700
Data Index: 1765295 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4440. Min Range: -6.4440
Max Act: 5.9127. Min Act: -0.1700
Data Index: 4547397 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4440. Min Range: -6.4440
Max Act: 5.9127. Min Act: -0.1700
Data Index: 8740569 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4440. Min Range: -6.4440
Max Act: 5.8815. Min Act: -0.1700
Data Index: 5261319 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4440. Min Range: -6.4440
Max Act: 5.8190. Min Act: -0.1700
Data Index: 2758407 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4440. Min Range: -6.4440
Max Act: 5.9127. Min Act: -0.1700
Data Index: 3762457 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4440. Min Range: -6.4440
Max Act: 5.7877. Min Act: -0.1700
Data Index: 8818665 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4440. Min Range: -6.4440
Max Act: 5.7252. Min Act: -0.1700
Data Index: 1836448 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4440. Min Range: -6.4440
Max Act: 5.7565. Min Act: -0.1700
Data Index: 3937417 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4440. Min Range: -6.4440
Max Act: 5.6940. Min Act: -0.1700
Data Index: 5551156 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4440. Min Range: -6.4440
Max Act: 5.7252. Min Act: -0.1700
Data Index: 2436867 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4440. Min Range: -6.4440
Max Act: 5.7252. Min Act: -0.1700
Data Index: 6976716 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4440. Min Range: -6.4440
Max Act: 5.6940. Min Act: -0.1700
Data Index: 7265120 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4440. Min Range: -6.4440
Max Act: 5.6940. Min Act: -0.1700
Data Index: 7937812 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4440. Min Range: -6.4440
Max Act: 5.6002. Min Act: -0.1700
Data Index: 1223409 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4440. Min Range: -6.4440
Max Act: 5.6627. Min Act: -0.1700
Data Index: 7448624 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4440. Min Range: -6.4440
Max Act: 5.6002. Min Act: -0.1700
Data Index: 8367752 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4440. Min Range: -6.4440
Max Act: 5.6315. Min Act: -0.1700
Data Index: 6784512 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4440. Min Range: -6.4440
Max Act: 5.6002. Min Act: -0.1700
Data Index: 8108183 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19