Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5716 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.5398. Min Act: -0.0000

Data Index: 609712 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.5414. Min Act: -0.0000

Data Index: 402572 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.5371. Min Act: -0.0000

Data Index: 243734 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.5160. Min Act: -0.0000

Data Index: 1035402 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.4625. Min Act: -0.0000

Data Index: 860970 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.4824. Min Act: -0.0000

Data Index: 1123843 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.5039. Min Act: -0.0000

Data Index: 1459289 (Python Code)

Max Activating Token Index: 855

Text #7

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.4633. Min Act: -0.0000

Data Index: 475551 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.4442. Min Act: -0.0000

Data Index: 564658 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.4475. Min Act: -0.0000

Data Index: 1264544 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.4455. Min Act: -0.0000

Data Index: 1537259 (Python Code)

Max Activating Token Index: 789

Text #11

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.4446. Min Act: -0.0000

Data Index: 232834 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.4270. Min Act: -0.0000

Data Index: 412192 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.4254. Min Act: -0.0000

Data Index: 896850 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.3913. Min Act: -0.0000

Data Index: 1149536 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.4172. Min Act: -0.0000

Data Index: 1273134 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.4313. Min Act: -0.0000

Data Index: 695574 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.4158. Min Act: -0.0000

Data Index: 774321 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.3827. Min Act: -0.0000

Data Index: 1325483 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.4121. Min Act: -0.0000

Data Index: 501384 (C4 (Web Text))

Max Activating Token Index: 136