Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5639 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0405. Min Range: -10.0405
Max Act: 10.0405. Min Act: -0.1700
Data Index: 1063710 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0405. Min Range: -10.0405
Max Act: 9.8530. Min Act: -0.1700
Data Index: 8165200 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0405. Min Range: -10.0405
Max Act: 9.6030. Min Act: -0.1700
Data Index: 3759323 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0405. Min Range: -10.0405
Max Act: 9.4780. Min Act: -0.1700
Data Index: 4691307 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0405. Min Range: -10.0405
Max Act: 9.3530. Min Act: -0.1700
Data Index: 4989338 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0405. Min Range: -10.0405
Max Act: 9.3530. Min Act: -0.1700
Data Index: 705481 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0405. Min Range: -10.0405
Max Act: 9.2905. Min Act: -0.1700
Data Index: 3957147 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0405. Min Range: -10.0405
Max Act: 9.2905. Min Act: -0.1700
Data Index: 4680211 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0405. Min Range: -10.0405
Max Act: 9.3530. Min Act: -0.1700
Data Index: 7276238 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0405. Min Range: -10.0405
Max Act: 9.2280. Min Act: -0.1699
Data Index: 1308336 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0405. Min Range: -10.0405
Max Act: 9.3530. Min Act: -0.1700
Data Index: 5039684 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0405. Min Range: -10.0405
Max Act: 9.2280. Min Act: -0.1700
Data Index: 8366998 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0405. Min Range: -10.0405
Max Act: 9.2280. Min Act: -0.1700
Data Index: 2985181 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0405. Min Range: -10.0405
Max Act: 9.2280. Min Act: -0.1700
Data Index: 417953 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0405. Min Range: -10.0405
Max Act: 9.1655. Min Act: -0.1700
Data Index: 2453731 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0405. Min Range: -10.0405
Max Act: 9.1030. Min Act: -0.1700
Data Index: 5461176 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0405. Min Range: -10.0405
Max Act: 9.1655. Min Act: -0.1700
Data Index: 5461178 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0405. Min Range: -10.0405
Max Act: 9.2280. Min Act: -0.1700
Data Index: 1714690 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0405. Min Range: -10.0405
Max Act: 9.1655. Min Act: -0.1700
Data Index: 8580746 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0405. Min Range: -10.0405
Max Act: 9.1030. Min Act: -0.1700
Data Index: 2632679 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #19