Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2677 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7270. Min Range: -6.7270
Max Act: 6.7270. Min Act: -0.1700
Data Index: 7146329 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7270. Min Range: -6.7270
Max Act: 6.5395. Min Act: -0.1700
Data Index: 7428718 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7270. Min Range: -6.7270
Max Act: 6.5082. Min Act: -0.1700
Data Index: 4871178 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7270. Min Range: -6.7270
Max Act: 6.4457. Min Act: -0.1700
Data Index: 8372396 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7270. Min Range: -6.7270
Max Act: 6.4145. Min Act: -0.1700
Data Index: 6685541 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7270. Min Range: -6.7270
Max Act: 6.3832. Min Act: -0.1700
Data Index: 5495739 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7270. Min Range: -6.7270
Max Act: 6.3520. Min Act: -0.1700
Data Index: 1428815 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7270. Min Range: -6.7270
Max Act: 6.3207. Min Act: -0.1700
Data Index: 5928835 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7270. Min Range: -6.7270
Max Act: 6.2582. Min Act: -0.1700
Data Index: 6270745 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7270. Min Range: -6.7270
Max Act: 6.2895. Min Act: -0.1700
Data Index: 65196 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7270. Min Range: -6.7270
Max Act: 6.2270. Min Act: -0.1700
Data Index: 7239588 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7270. Min Range: -6.7270
Max Act: 6.1957. Min Act: -0.1700
Data Index: 8811359 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7270. Min Range: -6.7270
Max Act: 6.1957. Min Act: -0.1700
Data Index: 7242440 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7270. Min Range: -6.7270
Max Act: 6.1645. Min Act: -0.1700
Data Index: 2805383 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7270. Min Range: -6.7270
Max Act: 6.1645. Min Act: -0.1700
Data Index: 1112593 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7270. Min Range: -6.7270
Max Act: 6.1645. Min Act: -0.1700
Data Index: 6893805 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7270. Min Range: -6.7270
Max Act: 6.1957. Min Act: -0.1700
Data Index: 8583753 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7270. Min Range: -6.7270
Max Act: 6.1332. Min Act: -0.1700
Data Index: 197539 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7270. Min Range: -6.7270
Max Act: 6.1332. Min Act: -0.1700
Data Index: 2688158 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7270. Min Range: -6.7270
Max Act: 6.1332. Min Act: -0.1700
Data Index: 5152144 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19