Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4439 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.9047. Min Act: -0.1700
Data Index: 6578831 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.9047. Min Act: -0.1700
Data Index: 3459859 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.7484. Min Act: -0.1700
Data Index: 5023303 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.7484. Min Act: -0.1700
Data Index: 4630460 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.6547. Min Act: -0.1700
Data Index: 2474274 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.6234. Min Act: -0.1700
Data Index: 2486086 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.5922. Min Act: -0.1700
Data Index: 8149276 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.5922. Min Act: -0.1700
Data Index: 8103806 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.5922. Min Act: -0.1700
Data Index: 898711 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.5922. Min Act: -0.1700
Data Index: 5401698 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.5297. Min Act: -0.1700
Data Index: 1068905 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.5297. Min Act: -0.1700
Data Index: 1795180 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.4672. Min Act: -0.1700
Data Index: 3241309 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.4672. Min Act: -0.1700
Data Index: 806912 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.4672. Min Act: -0.1700
Data Index: 7308063 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.4984. Min Act: -0.1700
Data Index: 1196626 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.4672. Min Act: -0.1700
Data Index: 6541591 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.4359. Min Act: -0.1700
Data Index: 4827029 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.4359. Min Act: -0.1700
Data Index: 6247590 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.4359. Min Act: -0.1700
Data Index: 3459177 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19