Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5805 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1440. Min Range: -5.1440
Max Act: 5.1440. Min Act: -0.1700
Data Index: 4635223 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1440. Min Range: -5.1440
Max Act: 5.1440. Min Act: -0.1700
Data Index: 1404792 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1440. Min Range: -5.1440
Max Act: 5.1127. Min Act: -0.1700
Data Index: 8270726 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1440. Min Range: -5.1440
Max Act: 5.1127. Min Act: -0.1700
Data Index: 3612662 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1440. Min Range: -5.1440
Max Act: 5.0502. Min Act: -0.1700
Data Index: 8310368 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1440. Min Range: -5.1440
Max Act: 5.0502. Min Act: -0.1700
Data Index: 8071974 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1440. Min Range: -5.1440
Max Act: 5.0815. Min Act: -0.1700
Data Index: 4434083 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1440. Min Range: -5.1440
Max Act: 5.0190. Min Act: -0.1700
Data Index: 4434076 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1440. Min Range: -5.1440
Max Act: 5.0502. Min Act: -0.1700
Data Index: 8577126 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1440. Min Range: -5.1440
Max Act: 5.0190. Min Act: -0.1700
Data Index: 862348 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1440. Min Range: -5.1440
Max Act: 5.0190. Min Act: -0.1700
Data Index: 5300395 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1440. Min Range: -5.1440
Max Act: 5.0190. Min Act: -0.1700
Data Index: 5333176 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1440. Min Range: -5.1440
Max Act: 5.0190. Min Act: -0.1700
Data Index: 6134713 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1440. Min Range: -5.1440
Max Act: 5.0190. Min Act: -0.1699
Data Index: 8010345 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1440. Min Range: -5.1440
Max Act: 5.0190. Min Act: -0.1700
Data Index: 8282205 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1440. Min Range: -5.1440
Max Act: 4.9877. Min Act: -0.1700
Data Index: 7659227 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1440. Min Range: -5.1440
Max Act: 4.9877. Min Act: -0.1700
Data Index: 2666429 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1440. Min Range: -5.1440
Max Act: 4.9877. Min Act: -0.1700
Data Index: 1897800 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1440. Min Range: -5.1440
Max Act: 4.9877. Min Act: -0.1700
Data Index: 1447441 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1440. Min Range: -5.1440
Max Act: 4.9877. Min Act: -0.1700
Data Index: 4600804 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19