Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 101 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5260. Min Range: -4.5260
Max Act: 4.5260. Min Act: -0.1700
Data Index: 1397140 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5260. Min Range: -4.5260
Max Act: 4.4947. Min Act: -0.1700
Data Index: 8830661 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5260. Min Range: -4.5260
Max Act: 4.4634. Min Act: -0.1700
Data Index: 1278079 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5260. Min Range: -4.5260
Max Act: 4.3697. Min Act: -0.1700
Data Index: 5054148 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5260. Min Range: -4.5260
Max Act: 4.3384. Min Act: -0.1700
Data Index: 7384146 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5260. Min Range: -4.5260
Max Act: 4.3384. Min Act: -0.1700
Data Index: 4068571 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5260. Min Range: -4.5260
Max Act: 4.3384. Min Act: -0.1700
Data Index: 2890926 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5260. Min Range: -4.5260
Max Act: 4.3697. Min Act: -0.1700
Data Index: 3270424 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5260. Min Range: -4.5260
Max Act: 4.3384. Min Act: -0.1700
Data Index: 68052 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5260. Min Range: -4.5260
Max Act: 4.3072. Min Act: -0.1700
Data Index: 5848415 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5260. Min Range: -4.5260
Max Act: 4.3384. Min Act: -0.1700
Data Index: 2148981 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5260. Min Range: -4.5260
Max Act: 4.2759. Min Act: -0.1700
Data Index: 1511949 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5260. Min Range: -4.5260
Max Act: 4.3072. Min Act: -0.1700
Data Index: 6299570 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5260. Min Range: -4.5260
Max Act: 4.3072. Min Act: -0.1700
Data Index: 8817091 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5260. Min Range: -4.5260
Max Act: 4.2759. Min Act: -0.1700
Data Index: 1555694 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5260. Min Range: -4.5260
Max Act: 4.2759. Min Act: -0.1700
Data Index: 559139 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5260. Min Range: -4.5260
Max Act: 4.3072. Min Act: -0.1700
Data Index: 1400157 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5260. Min Range: -4.5260
Max Act: 4.2759. Min Act: -0.1700
Data Index: 8639466 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5260. Min Range: -4.5260
Max Act: 4.2759. Min Act: -0.1700
Data Index: 850100 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5260. Min Range: -4.5260
Max Act: 4.2447. Min Act: -0.1700
Data Index: 2088544 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19