Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 135 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2424. Min Range: -8.2424
Max Act: 8.2424. Min Act: -0.1700
Data Index: 8155767 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2424. Min Range: -8.2424
Max Act: 8.1174. Min Act: -0.1700
Data Index: 7017930 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2424. Min Range: -8.2424
Max Act: 8.0237. Min Act: -0.1700
Data Index: 2597964 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2424. Min Range: -8.2424
Max Act: 8.0237. Min Act: -0.1700
Data Index: 4403326 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2424. Min Range: -8.2424
Max Act: 7.8987. Min Act: -0.1700
Data Index: 5050165 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2424. Min Range: -8.2424
Max Act: 7.8987. Min Act: -0.1700
Data Index: 1571601 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2424. Min Range: -8.2424
Max Act: 7.8987. Min Act: -0.1700
Data Index: 1581035 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2424. Min Range: -8.2424
Max Act: 7.8987. Min Act: -0.1700
Data Index: 3686381 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2424. Min Range: -8.2424
Max Act: 7.8362. Min Act: -0.1700
Data Index: 8701175 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2424. Min Range: -8.2424
Max Act: 7.8362. Min Act: -0.1700
Data Index: 498590 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2424. Min Range: -8.2424
Max Act: 7.8049. Min Act: -0.1700
Data Index: 252973 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2424. Min Range: -8.2424
Max Act: 7.7737. Min Act: -0.1700
Data Index: 6650633 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2424. Min Range: -8.2424
Max Act: 7.7737. Min Act: -0.1700
Data Index: 4321824 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2424. Min Range: -8.2424
Max Act: 7.7424. Min Act: -0.1700
Data Index: 2806945 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2424. Min Range: -8.2424
Max Act: 7.7112. Min Act: -0.1700
Data Index: 6890141 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2424. Min Range: -8.2424
Max Act: 7.7112. Min Act: -0.1700
Data Index: 62459 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2424. Min Range: -8.2424
Max Act: 7.6799. Min Act: -0.1700
Data Index: 4249731 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2424. Min Range: -8.2424
Max Act: 7.6799. Min Act: -0.1700
Data Index: 2270387 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2424. Min Range: -8.2424
Max Act: 7.6487. Min Act: -0.1700
Data Index: 6245932 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2424. Min Range: -8.2424
Max Act: 7.6174. Min Act: -0.1700
Data Index: 1241902 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19