Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1639 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9356. Min Range: -3.9356
Max Act: 3.9356. Min Act: -0.1700
Data Index: 5672540 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9356. Min Range: -3.9356
Max Act: 3.7792. Min Act: -0.1700
Data Index: 4591508 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9356. Min Range: -3.9356
Max Act: 3.7792. Min Act: -0.1700
Data Index: 8542594 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9356. Min Range: -3.9356
Max Act: 3.7479. Min Act: -0.1700
Data Index: 8116734 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9356. Min Range: -3.9356
Max Act: 3.6854. Min Act: -0.1700
Data Index: 1200886 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9356. Min Range: -3.9356
Max Act: 3.6228. Min Act: -0.1700
Data Index: 4309674 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9356. Min Range: -3.9356
Max Act: 3.6228. Min Act: -0.1700
Data Index: 6277901 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9356. Min Range: -3.9356
Max Act: 3.6228. Min Act: -0.1700
Data Index: 7247741 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9356. Min Range: -3.9356
Max Act: 3.5915. Min Act: -0.1700
Data Index: 3717251 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9356. Min Range: -3.9356
Max Act: 3.5915. Min Act: -0.1700
Data Index: 1210251 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9356. Min Range: -3.9356
Max Act: 3.5602. Min Act: -0.1700
Data Index: 5487860 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9356. Min Range: -3.9356
Max Act: 3.5602. Min Act: -0.1700
Data Index: 709458 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9356. Min Range: -3.9356
Max Act: 3.5602. Min Act: -0.1700
Data Index: 4123522 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9356. Min Range: -3.9356
Max Act: 3.5602. Min Act: -0.1700
Data Index: 870219 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9356. Min Range: -3.9356
Max Act: 3.5602. Min Act: -0.1700
Data Index: 7544103 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9356. Min Range: -3.9356
Max Act: 3.5602. Min Act: -0.1700
Data Index: 6025852 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9356. Min Range: -3.9356
Max Act: 3.5602. Min Act: -0.1700
Data Index: 1944846 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9356. Min Range: -3.9356
Max Act: 3.5289. Min Act: -0.1700
Data Index: 2460089 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9356. Min Range: -3.9356
Max Act: 3.4975. Min Act: -0.1700
Data Index: 1941085 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9356. Min Range: -3.9356
Max Act: 3.4975. Min Act: -0.1700
Data Index: 5505448 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19