Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1822 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.6967. Min Act: -0.0000

Data Index: 737526 (C4 (Web Text))

Max Activating Token Index: 632

Text #1

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5305. Min Act: -0.0001

Data Index: 1300060 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5059. Min Act: -0.0000

Data Index: 1282917 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5067. Min Act: -0.0000

Data Index: 940238 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4656. Min Act: -0.0001

Data Index: 1068173 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4737. Min Act: -0.0001

Data Index: 1070871 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4759. Min Act: -0.0000

Data Index: 820891 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4402. Min Act: -0.0001

Data Index: 990670 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4406. Min Act: -0.0000

Data Index: 865676 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4772. Min Act: -0.0001

Data Index: 491284 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4419. Min Act: -0.0000

Data Index: 1124601 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.3836. Min Act: -0.0001

Data Index: 1316647 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4225. Min Act: -0.0001

Data Index: 510410 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4323. Min Act: -0.0001

Data Index: 1242002 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4181. Min Act: -0.0000

Data Index: 1160537 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4286. Min Act: -0.0001

Data Index: 546466 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4430. Min Act: -0.0000

Data Index: 100091 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4381. Min Act: -0.0000

Data Index: 1029780 (C4 (Web Text))

Max Activating Token Index: 431

Text #18

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4229. Min Act: -0.0001

Data Index: 1161976 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4164. Min Act: -0.0001

Data Index: 1128843 (C4 (Web Text))

Max Activating Token Index: 757