Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2542 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5196. Min Range: -5.5196
Max Act: 5.5196. Min Act: -0.1700
Data Index: 1986936 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5196. Min Range: -5.5196
Max Act: 5.4884. Min Act: -0.1700
Data Index: 3051877 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5196. Min Range: -5.5196
Max Act: 5.4259. Min Act: -0.1700
Data Index: 1986946 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5196. Min Range: -5.5196
Max Act: 5.3634. Min Act: -0.1700
Data Index: 7725124 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5196. Min Range: -5.5196
Max Act: 5.3946. Min Act: -0.1700
Data Index: 4277538 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5196. Min Range: -5.5196
Max Act: 5.3321. Min Act: -0.1700
Data Index: 457594 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5196. Min Range: -5.5196
Max Act: 5.3634. Min Act: -0.1700
Data Index: 5075569 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5196. Min Range: -5.5196
Max Act: 5.2696. Min Act: -0.1700
Data Index: 7457352 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5196. Min Range: -5.5196
Max Act: 5.2071. Min Act: -0.1700
Data Index: 6063627 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5196. Min Range: -5.5196
Max Act: 5.2384. Min Act: -0.1700
Data Index: 1986947 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5196. Min Range: -5.5196
Max Act: 5.2071. Min Act: -0.1700
Data Index: 227522 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5196. Min Range: -5.5196
Max Act: 5.1759. Min Act: -0.1700
Data Index: 1986933 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5196. Min Range: -5.5196
Max Act: 5.2071. Min Act: -0.1700
Data Index: 5289877 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5196. Min Range: -5.5196
Max Act: 5.1446. Min Act: -0.1700
Data Index: 2591539 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5196. Min Range: -5.5196
Max Act: 5.1759. Min Act: -0.1700
Data Index: 3051881 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5196. Min Range: -5.5196
Max Act: 5.1446. Min Act: -0.1700
Data Index: 4370121 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5196. Min Range: -5.5196
Max Act: 5.1446. Min Act: -0.1700
Data Index: 227525 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5196. Min Range: -5.5196
Max Act: 5.1446. Min Act: -0.1700
Data Index: 6727521 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5196. Min Range: -5.5196
Max Act: 5.1759. Min Act: -0.1700
Data Index: 2853822 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5196. Min Range: -5.5196
Max Act: 5.1759. Min Act: -0.1700
Data Index: 1986952 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19