Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 11 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5380. Min Range: -6.5380
Max Act: 6.5380. Min Act: -0.1700
Data Index: 8352267 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5380. Min Range: -6.5380
Max Act: 6.5067. Min Act: -0.1700
Data Index: 3307179 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5380. Min Range: -6.5380
Max Act: 6.3505. Min Act: -0.1700
Data Index: 5137912 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5380. Min Range: -6.5380
Max Act: 6.3505. Min Act: -0.1700
Data Index: 554749 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5380. Min Range: -6.5380
Max Act: 6.1942. Min Act: -0.1700
Data Index: 5126228 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5380. Min Range: -6.5380
Max Act: 6.1942. Min Act: -0.1700
Data Index: 874443 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5380. Min Range: -6.5380
Max Act: 6.1942. Min Act: -0.1700
Data Index: 85608 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5380. Min Range: -6.5380
Max Act: 6.1630. Min Act: -0.1700
Data Index: 8686400 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5380. Min Range: -6.5380
Max Act: 6.1317. Min Act: -0.1700
Data Index: 6702904 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5380. Min Range: -6.5380
Max Act: 6.1317. Min Act: -0.1700
Data Index: 3817427 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5380. Min Range: -6.5380
Max Act: 6.1005. Min Act: -0.1700
Data Index: 2159474 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5380. Min Range: -6.5380
Max Act: 6.1005. Min Act: -0.1700
Data Index: 8387931 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5380. Min Range: -6.5380
Max Act: 6.0692. Min Act: -0.1700
Data Index: 6488907 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5380. Min Range: -6.5380
Max Act: 6.0692. Min Act: -0.1700
Data Index: 7248581 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5380. Min Range: -6.5380
Max Act: 6.0380. Min Act: -0.1700
Data Index: 230616 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5380. Min Range: -6.5380
Max Act: 6.0380. Min Act: -0.1700
Data Index: 1955069 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5380. Min Range: -6.5380
Max Act: 6.0380. Min Act: -0.1700
Data Index: 5213734 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5380. Min Range: -6.5380
Max Act: 6.0380. Min Act: -0.1700
Data Index: 4964228 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5380. Min Range: -6.5380
Max Act: 6.0380. Min Act: -0.1700
Data Index: 544836 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5380. Min Range: -6.5380
Max Act: 6.0067. Min Act: -0.1700
Data Index: 6527498 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19