Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2494 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.6736. Min Range: -10.6736
Max Act: 10.6736. Min Act: -0.1700
Data Index: 8338298 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6736. Min Range: -10.6736
Max Act: 10.2986. Min Act: -0.1700
Data Index: 8827114 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6736. Min Range: -10.6736
Max Act: 10.1111. Min Act: -0.1700
Data Index: 1835392 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6736. Min Range: -10.6736
Max Act: 10.0486. Min Act: -0.1700
Data Index: 7017114 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6736. Min Range: -10.6736
Max Act: 9.9861. Min Act: -0.1700
Data Index: 6153624 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6736. Min Range: -10.6736
Max Act: 9.7986. Min Act: -0.1700
Data Index: 5136380 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6736. Min Range: -10.6736
Max Act: 9.7986. Min Act: -0.1700
Data Index: 879251 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6736. Min Range: -10.6736
Max Act: 9.7986. Min Act: -0.1700
Data Index: 6079696 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6736. Min Range: -10.6736
Max Act: 9.7361. Min Act: -0.1700
Data Index: 2914478 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6736. Min Range: -10.6736
Max Act: 9.6736. Min Act: -0.1700
Data Index: 1221287 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6736. Min Range: -10.6736
Max Act: 9.6736. Min Act: -0.1700
Data Index: 5211132 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6736. Min Range: -10.6736
Max Act: 9.7361. Min Act: -0.1700
Data Index: 422125 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6736. Min Range: -10.6736
Max Act: 9.6736. Min Act: -0.1700
Data Index: 5532243 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6736. Min Range: -10.6736
Max Act: 9.6736. Min Act: -0.1700
Data Index: 5009726 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6736. Min Range: -10.6736
Max Act: 9.6736. Min Act: -0.1700
Data Index: 5038799 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6736. Min Range: -10.6736
Max Act: 9.6111. Min Act: -0.1700
Data Index: 5190575 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6736. Min Range: -10.6736
Max Act: 9.6111. Min Act: -0.1700
Data Index: 6374435 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6736. Min Range: -10.6736
Max Act: 9.6111. Min Act: -0.1700
Data Index: 4859287 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6736. Min Range: -10.6736
Max Act: 9.6111. Min Act: -0.1700
Data Index: 2621246 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6736. Min Range: -10.6736
Max Act: 9.6111. Min Act: -0.1700
Data Index: 1000791 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #19