Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2766 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7366. Min Range: -2.7366
Max Act: 2.7366. Min Act: -0.1700
Data Index: 760020 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7366. Min Range: -2.7366
Max Act: 2.7046. Min Act: -0.1700
Data Index: 818886 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7366. Min Range: -2.7366
Max Act: 2.6726. Min Act: -0.1700
Data Index: 787518 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7366. Min Range: -2.7366
Max Act: 2.6405. Min Act: -0.1700
Data Index: 4796035 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7366. Min Range: -2.7366
Max Act: 2.5923. Min Act: -0.1700
Data Index: 5457957 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7366. Min Range: -2.7366
Max Act: 2.5923. Min Act: -0.1700
Data Index: 7079951 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7366. Min Range: -2.7366
Max Act: 2.5601. Min Act: -0.1700
Data Index: 1508718 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7366. Min Range: -2.7366
Max Act: 2.5601. Min Act: -0.1700
Data Index: 5699585 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7366. Min Range: -2.7366
Max Act: 2.5439. Min Act: -0.1700
Data Index: 4046772 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7366. Min Range: -2.7366
Max Act: 2.5278. Min Act: -0.1700
Data Index: 4071936 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7366. Min Range: -2.7366
Max Act: 2.5439. Min Act: -0.1700
Data Index: 4449761 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7366. Min Range: -2.7366
Max Act: 2.5116. Min Act: -0.1700
Data Index: 617402 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7366. Min Range: -2.7366
Max Act: 2.5116. Min Act: -0.1700
Data Index: 4536162 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7366. Min Range: -2.7366
Max Act: 2.5116. Min Act: -0.1700
Data Index: 3591998 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7366. Min Range: -2.7366
Max Act: 2.5116. Min Act: -0.1700
Data Index: 3878336 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7366. Min Range: -2.7366
Max Act: 2.5116. Min Act: -0.1700
Data Index: 8471331 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7366. Min Range: -2.7366
Max Act: 2.4954. Min Act: -0.1700
Data Index: 7257789 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7366. Min Range: -2.7366
Max Act: 2.4954. Min Act: -0.1700
Data Index: 2279763 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7366. Min Range: -2.7366
Max Act: 2.4954. Min Act: -0.1700
Data Index: 6462950 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7366. Min Range: -2.7366
Max Act: 2.4792. Min Act: -0.1700
Data Index: 8353378 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #19