Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4823 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4793. Min Range: -7.4793
Max Act: 7.4793. Min Act: -0.1700
Data Index: 5309652 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4793. Min Range: -7.4793
Max Act: 7.3856. Min Act: -0.1700
Data Index: 8211002 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4793. Min Range: -7.4793
Max Act: 7.1981. Min Act: -0.1700
Data Index: 5299560 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4793. Min Range: -7.4793
Max Act: 7.1356. Min Act: -0.1700
Data Index: 7789224 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4793. Min Range: -7.4793
Max Act: 7.0731. Min Act: -0.1700
Data Index: 3201317 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4793. Min Range: -7.4793
Max Act: 7.0731. Min Act: -0.1700
Data Index: 8089958 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4793. Min Range: -7.4793
Max Act: 7.0731. Min Act: -0.1700
Data Index: 5212542 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4793. Min Range: -7.4793
Max Act: 7.0731. Min Act: -0.1700
Data Index: 4459320 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4793. Min Range: -7.4793
Max Act: 7.0418. Min Act: -0.1700
Data Index: 175274 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4793. Min Range: -7.4793
Max Act: 7.0106. Min Act: -0.1700
Data Index: 5481896 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4793. Min Range: -7.4793
Max Act: 7.0106. Min Act: -0.1700
Data Index: 495198 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4793. Min Range: -7.4793
Max Act: 7.0106. Min Act: -0.1700
Data Index: 3724988 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4793. Min Range: -7.4793
Max Act: 7.0106. Min Act: -0.1700
Data Index: 1987528 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4793. Min Range: -7.4793
Max Act: 6.9793. Min Act: -0.1700
Data Index: 6117112 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4793. Min Range: -7.4793
Max Act: 6.9793. Min Act: -0.1700
Data Index: 4377338 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4793. Min Range: -7.4793
Max Act: 6.9481. Min Act: -0.1700
Data Index: 6145351 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4793. Min Range: -7.4793
Max Act: 6.9481. Min Act: -0.1700
Data Index: 5555292 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4793. Min Range: -7.4793
Max Act: 6.9481. Min Act: -0.1700
Data Index: 4032014 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4793. Min Range: -7.4793
Max Act: 6.9168. Min Act: -0.1700
Data Index: 2831553 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4793. Min Range: -7.4793
Max Act: 6.8856. Min Act: -0.1700
Data Index: 1031849 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19