Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3383 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1108. Min Range: -4.1108
Max Act: 4.1108. Min Act: -0.1700
Data Index: 292851 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1108. Min Range: -4.1108
Max Act: 4.0170. Min Act: -0.1700
Data Index: 165534 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1108. Min Range: -4.1108
Max Act: 4.0170. Min Act: -0.1700
Data Index: 1838303 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1108. Min Range: -4.1108
Max Act: 3.8607. Min Act: -0.1700
Data Index: 7180831 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1108. Min Range: -4.1108
Max Act: 3.8607. Min Act: -0.1700
Data Index: 3993447 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1108. Min Range: -4.1108
Max Act: 3.7981. Min Act: -0.1700
Data Index: 6469451 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1108. Min Range: -4.1108
Max Act: 3.8294. Min Act: -0.1700
Data Index: 6626678 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1108. Min Range: -4.1108
Max Act: 3.7981. Min Act: -0.1700
Data Index: 4951731 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1108. Min Range: -4.1108
Max Act: 3.7981. Min Act: -0.1700
Data Index: 4791273 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1108. Min Range: -4.1108
Max Act: 3.7981. Min Act: -0.1700
Data Index: 7053078 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1108. Min Range: -4.1108
Max Act: 3.7981. Min Act: -0.1700
Data Index: 3072288 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1108. Min Range: -4.1108
Max Act: 3.7356. Min Act: -0.1700
Data Index: 432386 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1108. Min Range: -4.1108
Max Act: 3.8294. Min Act: -0.1700
Data Index: 550887 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1108. Min Range: -4.1108
Max Act: 3.7669. Min Act: -0.1700
Data Index: 7290582 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1108. Min Range: -4.1108
Max Act: 3.7981. Min Act: -0.1700
Data Index: 7260624 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1108. Min Range: -4.1108
Max Act: 3.7981. Min Act: -0.1700
Data Index: 2826461 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1108. Min Range: -4.1108
Max Act: 3.7669. Min Act: -0.1700
Data Index: 1181127 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1108. Min Range: -4.1108
Max Act: 3.7669. Min Act: -0.1700
Data Index: 462855 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1108. Min Range: -4.1108
Max Act: 3.7981. Min Act: -0.1700
Data Index: 1437374 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1108. Min Range: -4.1108
Max Act: 3.7669. Min Act: -0.1700
Data Index: 5572814 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19