Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3766 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2954. Min Range: -8.2954
Max Act: 8.2954. Min Act: -0.1700
Data Index: 1811618 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2954. Min Range: -8.2954
Max Act: 7.8266. Min Act: -0.1700
Data Index: 5273462 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2954. Min Range: -8.2954
Max Act: 7.7329. Min Act: -0.1700
Data Index: 5734310 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2954. Min Range: -8.2954
Max Act: 7.6704. Min Act: -0.1700
Data Index: 5901470 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2954. Min Range: -8.2954
Max Act: 7.6704. Min Act: -0.1700
Data Index: 2930536 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2954. Min Range: -8.2954
Max Act: 7.6079. Min Act: -0.1700
Data Index: 7117763 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2954. Min Range: -8.2954
Max Act: 7.6391. Min Act: -0.1700
Data Index: 6897633 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2954. Min Range: -8.2954
Max Act: 7.5766. Min Act: -0.1700
Data Index: 599628 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2954. Min Range: -8.2954
Max Act: 7.5454. Min Act: -0.1700
Data Index: 3466518 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2954. Min Range: -8.2954
Max Act: 7.5454. Min Act: -0.1700
Data Index: 637011 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2954. Min Range: -8.2954
Max Act: 7.4829. Min Act: -0.1700
Data Index: 1880761 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2954. Min Range: -8.2954
Max Act: 7.4829. Min Act: -0.1700
Data Index: 4339713 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2954. Min Range: -8.2954
Max Act: 7.5141. Min Act: -0.1700
Data Index: 8593127 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2954. Min Range: -8.2954
Max Act: 7.5454. Min Act: -0.1700
Data Index: 6718398 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2954. Min Range: -8.2954
Max Act: 7.5141. Min Act: -0.1700
Data Index: 8086580 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2954. Min Range: -8.2954
Max Act: 7.5141. Min Act: -0.1700
Data Index: 7272277 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2954. Min Range: -8.2954
Max Act: 7.4829. Min Act: -0.1700
Data Index: 4063462 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2954. Min Range: -8.2954
Max Act: 7.4516. Min Act: -0.1700
Data Index: 7534708 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2954. Min Range: -8.2954
Max Act: 7.4829. Min Act: -0.1700
Data Index: 2847158 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2954. Min Range: -8.2954
Max Act: 7.4516. Min Act: -0.1700
Data Index: 6404051 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19