Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2674 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6741. Min Range: -2.6741
Max Act: 2.6741. Min Act: -0.1700
Data Index: 7176472 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6741. Min Range: -2.6741
Max Act: 2.6501. Min Act: -0.1700
Data Index: 1788481 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6741. Min Range: -2.6741
Max Act: 2.6501. Min Act: -0.1700
Data Index: 7413125 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6741. Min Range: -2.6741
Max Act: 2.6260. Min Act: -0.1700
Data Index: 1034528 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6741. Min Range: -2.6741
Max Act: 2.6260. Min Act: -0.1700
Data Index: 3913074 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6741. Min Range: -2.6741
Max Act: 2.6019. Min Act: -0.1700
Data Index: 1032499 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6741. Min Range: -2.6741
Max Act: 2.6019. Min Act: -0.1700
Data Index: 7314335 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6741. Min Range: -2.6741
Max Act: 2.5938. Min Act: -0.1700
Data Index: 2657694 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6741. Min Range: -2.6741
Max Act: 2.5777. Min Act: -0.1700
Data Index: 6596855 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6741. Min Range: -2.6741
Max Act: 2.5938. Min Act: -0.1700
Data Index: 6217218 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6741. Min Range: -2.6741
Max Act: 2.5858. Min Act: -0.1700
Data Index: 3805581 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6741. Min Range: -2.6741
Max Act: 2.5777. Min Act: -0.1700
Data Index: 6249433 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6741. Min Range: -2.6741
Max Act: 2.5616. Min Act: -0.1700
Data Index: 4382262 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6741. Min Range: -2.6741
Max Act: 2.5697. Min Act: -0.1700
Data Index: 8036655 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6741. Min Range: -2.6741
Max Act: 2.5616. Min Act: -0.1700
Data Index: 8086943 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6741. Min Range: -2.6741
Max Act: 2.5697. Min Act: -0.1700
Data Index: 3186846 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6741. Min Range: -2.6741
Max Act: 2.5616. Min Act: -0.1700
Data Index: 5503904 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6741. Min Range: -2.6741
Max Act: 2.5535. Min Act: -0.1700
Data Index: 7590794 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6741. Min Range: -2.6741
Max Act: 2.5535. Min Act: -0.1700
Data Index: 1788478 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6741. Min Range: -2.6741
Max Act: 2.5535. Min Act: -0.1700
Data Index: 6361444 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19