Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1953 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3102. Min Range: -4.3102
Max Act: 4.2790. Min Act: -0.1700
Data Index: 8357463 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3102. Min Range: -4.3102
Max Act: 4.2790. Min Act: -0.1700
Data Index: 1577244 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3102. Min Range: -4.3102
Max Act: 4.2477. Min Act: -0.1700
Data Index: 2029224 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3102. Min Range: -4.3102
Max Act: 4.3102. Min Act: -0.1700
Data Index: 1807310 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3102. Min Range: -4.3102
Max Act: 4.2009. Min Act: -0.1700
Data Index: 1920006 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3102. Min Range: -4.3102
Max Act: 4.1696. Min Act: -0.1700
Data Index: 495560 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3102. Min Range: -4.3102
Max Act: 4.0446. Min Act: -0.1700
Data Index: 158326 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3102. Min Range: -4.3102
Max Act: 4.0602. Min Act: -0.1700
Data Index: 3701481 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3102. Min Range: -4.3102
Max Act: 4.0289. Min Act: -0.1700
Data Index: 2363088 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3102. Min Range: -4.3102
Max Act: 4.0289. Min Act: -0.1700
Data Index: 1775537 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3102. Min Range: -4.3102
Max Act: 4.0289. Min Act: -0.1700
Data Index: 4079076 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3102. Min Range: -4.3102
Max Act: 4.0289. Min Act: -0.1700
Data Index: 117400 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3102. Min Range: -4.3102
Max Act: 4.0133. Min Act: -0.1700
Data Index: 5133616 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3102. Min Range: -4.3102
Max Act: 3.9977. Min Act: -0.1700
Data Index: 2969533 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3102. Min Range: -4.3102
Max Act: 3.9508. Min Act: -0.1700
Data Index: 7896041 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3102. Min Range: -4.3102
Max Act: 3.9039. Min Act: -0.1700
Data Index: 8294622 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3102. Min Range: -4.3102
Max Act: 3.9195. Min Act: -0.1700
Data Index: 8733500 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3102. Min Range: -4.3102
Max Act: 3.9039. Min Act: -0.1700
Data Index: 1266338 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3102. Min Range: -4.3102
Max Act: 3.9352. Min Act: -0.1700
Data Index: 2219651 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3102. Min Range: -4.3102
Max Act: 3.9195. Min Act: -0.1700
Data Index: 428341 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19