Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3909 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.5031. Min Act: -0.0000

Data Index: 1015280 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4984. Min Act: -0.0000

Data Index: 1051483 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4392. Min Act: -0.0000

Data Index: 82090 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4742. Min Act: -0.0000

Data Index: 816956 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4433. Min Act: -0.0000

Data Index: 548868 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4645. Min Act: -0.0000

Data Index: 1023838 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4284. Min Act: -0.0000

Data Index: 598757 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4423. Min Act: -0.0000

Data Index: 1455630 (Python Code)

Max Activating Token Index: 855

Text #8

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4442. Min Act: -0.0000

Data Index: 493216 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4192. Min Act: -0.0000

Data Index: 1586546 (Python Code)

Max Activating Token Index: 132

Text #10

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4197. Min Act: -0.0000

Data Index: 1445866 (Python Code)

Max Activating Token Index: 942

Text #11

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4158. Min Act: -0.0000

Data Index: 1607692 (Python Code)

Max Activating Token Index: 163

Text #12

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4409. Min Act: -0.0000

Data Index: 1406347 (Python Code)

Max Activating Token Index: 689

Text #13

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.3840. Min Act: -0.0000

Data Index: 1643788 (Python Code)

Max Activating Token Index: 976

Text #14

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4365. Min Act: -0.0000

Data Index: 777376 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4020. Min Act: -0.0000

Data Index: 1078829 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4168. Min Act: -0.0000

Data Index: 743143 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.3946. Min Act: -0.0000

Data Index: 1413416 (Python Code)

Max Activating Token Index: 1008

Text #18

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4117. Min Act: -0.0000

Data Index: 1402818 (Python Code)

Max Activating Token Index: 242

Text #19

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4085. Min Act: -0.0000

Data Index: 1368049 (Python Code)

Max Activating Token Index: 726