Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 891 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5113. Min Range: -4.5113
Max Act: 4.5113. Min Act: -0.1700
Data Index: 5406607 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5113. Min Range: -4.5113
Max Act: 4.4175. Min Act: -0.1700
Data Index: 3718301 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5113. Min Range: -4.5113
Max Act: 4.2613. Min Act: -0.1700
Data Index: 4977693 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5113. Min Range: -4.5113
Max Act: 4.2300. Min Act: -0.1700
Data Index: 8060893 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5113. Min Range: -4.5113
Max Act: 4.1988. Min Act: -0.1700
Data Index: 771417 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5113. Min Range: -4.5113
Max Act: 4.1988. Min Act: -0.1700
Data Index: 4823455 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5113. Min Range: -4.5113
Max Act: 4.1988. Min Act: -0.1700
Data Index: 6450656 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5113. Min Range: -4.5113
Max Act: 4.1675. Min Act: -0.1700
Data Index: 7585000 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5113. Min Range: -4.5113
Max Act: 4.1675. Min Act: -0.1700
Data Index: 5058526 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5113. Min Range: -4.5113
Max Act: 4.1362. Min Act: -0.1700
Data Index: 5255851 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5113. Min Range: -4.5113
Max Act: 4.1362. Min Act: -0.1700
Data Index: 5224533 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5113. Min Range: -4.5113
Max Act: 4.1362. Min Act: -0.1700
Data Index: 3791791 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5113. Min Range: -4.5113
Max Act: 4.1362. Min Act: -0.1700
Data Index: 1548643 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5113. Min Range: -4.5113
Max Act: 4.1050. Min Act: -0.1700
Data Index: 4575539 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5113. Min Range: -4.5113
Max Act: 4.0737. Min Act: -0.1700
Data Index: 8294135 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5113. Min Range: -4.5113
Max Act: 4.1050. Min Act: -0.1700
Data Index: 385341 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5113. Min Range: -4.5113
Max Act: 4.1050. Min Act: -0.1700
Data Index: 7923335 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5113. Min Range: -4.5113
Max Act: 4.1050. Min Act: -0.1700
Data Index: 3540760 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5113. Min Range: -4.5113
Max Act: 4.1362. Min Act: -0.1700
Data Index: 5336110 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5113. Min Range: -4.5113
Max Act: 4.1050. Min Act: -0.1700
Data Index: 321504 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19