Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2321 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5579. Min Range: -8.5579
Max Act: 8.5579. Min Act: -0.1700
Data Index: 5028862 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5579. Min Range: -8.5579
Max Act: 8.4954. Min Act: -0.1700
Data Index: 6777259 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5579. Min Range: -8.5579
Max Act: 8.4329. Min Act: -0.1700
Data Index: 53689 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5579. Min Range: -8.5579
Max Act: 8.4329. Min Act: -0.1700
Data Index: 6086142 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5579. Min Range: -8.5579
Max Act: 8.4329. Min Act: -0.1700
Data Index: 4625114 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5579. Min Range: -8.5579
Max Act: 8.3079. Min Act: -0.1700
Data Index: 3118507 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5579. Min Range: -8.5579
Max Act: 8.2454. Min Act: -0.1700
Data Index: 3545600 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5579. Min Range: -8.5579
Max Act: 8.2454. Min Act: -0.1700
Data Index: 5682915 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5579. Min Range: -8.5579
Max Act: 8.3079. Min Act: -0.1700
Data Index: 5214547 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5579. Min Range: -8.5579
Max Act: 8.2454. Min Act: -0.1700
Data Index: 6888644 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5579. Min Range: -8.5579
Max Act: 8.1829. Min Act: -0.1700
Data Index: 6141767 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5579. Min Range: -8.5579
Max Act: 8.1829. Min Act: -0.1700
Data Index: 6245502 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5579. Min Range: -8.5579
Max Act: 8.1829. Min Act: -0.1700
Data Index: 6179127 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5579. Min Range: -8.5579
Max Act: 8.0579. Min Act: -0.1700
Data Index: 2165 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5579. Min Range: -8.5579
Max Act: 8.1204. Min Act: -0.1700
Data Index: 2985899 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5579. Min Range: -8.5579
Max Act: 8.1204. Min Act: -0.1700
Data Index: 8802565 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5579. Min Range: -8.5579
Max Act: 8.0579. Min Act: -0.1700
Data Index: 6668262 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5579. Min Range: -8.5579
Max Act: 8.0579. Min Act: -0.1700
Data Index: 6374418 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5579. Min Range: -8.5579
Max Act: 8.0579. Min Act: -0.1700
Data Index: 4012628 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5579. Min Range: -8.5579
Max Act: 8.0579. Min Act: -0.1700
Data Index: 6899147 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19