Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5637 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5981. Min Range: -7.5981
Max Act: 7.5669. Min Act: -0.1700
Data Index: 4778897 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5981. Min Range: -7.5981
Max Act: 7.5669. Min Act: -0.1700
Data Index: 3569389 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5981. Min Range: -7.5981
Max Act: 7.5669. Min Act: -0.1700
Data Index: 7359527 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5981. Min Range: -7.5981
Max Act: 7.5669. Min Act: -0.1700
Data Index: 7114080 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5981. Min Range: -7.5981
Max Act: 7.5669. Min Act: -0.1700
Data Index: 2943326 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5981. Min Range: -7.5981
Max Act: 7.5981. Min Act: -0.1700
Data Index: 138272 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5981. Min Range: -7.5981
Max Act: 7.5669. Min Act: -0.1700
Data Index: 7823411 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5981. Min Range: -7.5981
Max Act: 7.5356. Min Act: -0.1700
Data Index: 3753216 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5981. Min Range: -7.5981
Max Act: 7.5356. Min Act: -0.1700
Data Index: 915803 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5981. Min Range: -7.5981
Max Act: 7.5356. Min Act: -0.1700
Data Index: 966598 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5981. Min Range: -7.5981
Max Act: 7.5044. Min Act: -0.1700
Data Index: 247688 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5981. Min Range: -7.5981
Max Act: 7.4731. Min Act: -0.1700
Data Index: 6875948 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5981. Min Range: -7.5981
Max Act: 7.4731. Min Act: -0.1700
Data Index: 4114737 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5981. Min Range: -7.5981
Max Act: 7.4731. Min Act: -0.1700
Data Index: 4126447 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5981. Min Range: -7.5981
Max Act: 7.4731. Min Act: -0.1700
Data Index: 1141507 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5981. Min Range: -7.5981
Max Act: 7.4419. Min Act: -0.1700
Data Index: 5198617 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5981. Min Range: -7.5981
Max Act: 7.4419. Min Act: -0.1700
Data Index: 3626914 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5981. Min Range: -7.5981
Max Act: 7.4419. Min Act: -0.1700
Data Index: 4700255 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5981. Min Range: -7.5981
Max Act: 7.4419. Min Act: -0.1700
Data Index: 3684615 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5981. Min Range: -7.5981
Max Act: 7.4419. Min Act: -0.1700
Data Index: 1748887 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19