Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2989 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3268. Min Range: -5.3268
Max Act: 5.3268. Min Act: -0.1700
Data Index: 8092724 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3268. Min Range: -5.3268
Max Act: 5.3268. Min Act: -0.1700
Data Index: 1819660 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3268. Min Range: -5.3268
Max Act: 5.2018. Min Act: -0.1700
Data Index: 7006788 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3268. Min Range: -5.3268
Max Act: 5.1081. Min Act: -0.1700
Data Index: 4344015 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3268. Min Range: -5.3268
Max Act: 5.1393. Min Act: -0.1700
Data Index: 6276802 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3268. Min Range: -5.3268
Max Act: 5.1081. Min Act: -0.1700
Data Index: 3751709 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3268. Min Range: -5.3268
Max Act: 5.0768. Min Act: -0.1700
Data Index: 1497076 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3268. Min Range: -5.3268
Max Act: 5.0456. Min Act: -0.1700
Data Index: 7510691 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3268. Min Range: -5.3268
Max Act: 5.0456. Min Act: -0.1700
Data Index: 7746666 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3268. Min Range: -5.3268
Max Act: 5.0143. Min Act: -0.1700
Data Index: 7770206 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3268. Min Range: -5.3268
Max Act: 5.0456. Min Act: -0.1700
Data Index: 5153606 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3268. Min Range: -5.3268
Max Act: 4.9831. Min Act: -0.1700
Data Index: 7939590 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3268. Min Range: -5.3268
Max Act: 4.9518. Min Act: -0.1700
Data Index: 8076683 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3268. Min Range: -5.3268
Max Act: 4.9831. Min Act: -0.1700
Data Index: 6325207 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3268. Min Range: -5.3268
Max Act: 4.9831. Min Act: -0.1700
Data Index: 1990375 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3268. Min Range: -5.3268
Max Act: 4.9831. Min Act: -0.1700
Data Index: 6186087 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3268. Min Range: -5.3268
Max Act: 4.9518. Min Act: -0.1700
Data Index: 3289399 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3268. Min Range: -5.3268
Max Act: 4.9206. Min Act: -0.1700
Data Index: 2247660 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3268. Min Range: -5.3268
Max Act: 4.8893. Min Act: -0.1700
Data Index: 397347 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3268. Min Range: -5.3268
Max Act: 4.9206. Min Act: -0.1700
Data Index: 6376341 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19