Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4271 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8625. Min Range: -5.8625
Max Act: 5.8625. Min Act: -0.1700
Data Index: 5098529 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8625. Min Range: -5.8625
Max Act: 5.6125. Min Act: -0.1700
Data Index: 234481 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8625. Min Range: -5.8625
Max Act: 5.3937. Min Act: -0.1700
Data Index: 4771355 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8625. Min Range: -5.8625
Max Act: 5.3937. Min Act: -0.1700
Data Index: 8142643 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8625. Min Range: -5.8625
Max Act: 5.3937. Min Act: -0.1700
Data Index: 2452000 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8625. Min Range: -5.8625
Max Act: 5.3312. Min Act: -0.1700
Data Index: 5891804 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8625. Min Range: -5.8625
Max Act: 5.3625. Min Act: -0.1700
Data Index: 1391087 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8625. Min Range: -5.8625
Max Act: 5.2687. Min Act: -0.1700
Data Index: 3267379 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8625. Min Range: -5.8625
Max Act: 5.2687. Min Act: -0.1700
Data Index: 4542392 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8625. Min Range: -5.8625
Max Act: 5.2375. Min Act: -0.1700
Data Index: 7031889 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8625. Min Range: -5.8625
Max Act: 5.2375. Min Act: -0.1700
Data Index: 8604633 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8625. Min Range: -5.8625
Max Act: 5.2375. Min Act: -0.1700
Data Index: 8580851 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8625. Min Range: -5.8625
Max Act: 5.2375. Min Act: -0.1700
Data Index: 7540091 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8625. Min Range: -5.8625
Max Act: 5.2062. Min Act: -0.1700
Data Index: 2260452 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8625. Min Range: -5.8625
Max Act: 5.2062. Min Act: -0.1700
Data Index: 6801803 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8625. Min Range: -5.8625
Max Act: 5.2062. Min Act: -0.1700
Data Index: 588939 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8625. Min Range: -5.8625
Max Act: 5.1750. Min Act: -0.1700
Data Index: 8639614 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8625. Min Range: -5.8625
Max Act: 5.1437. Min Act: -0.1700
Data Index: 1388401 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8625. Min Range: -5.8625
Max Act: 5.1125. Min Act: -0.1700
Data Index: 172063 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8625. Min Range: -5.8625
Max Act: 5.1437. Min Act: -0.1700
Data Index: 562008 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19