Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2001 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.3653. Min Act: -0.0000

Data Index: 1043623 (The Pile)

Max Activating Token Index: 208

Text #1

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.3249. Min Act: -0.0000

Data Index: 130998 (The Pile)

Max Activating Token Index: 772

Text #2

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.2672. Min Act: -0.0000

Data Index: 1943078 (The Pile)

Max Activating Token Index: 916

Text #3

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.2513. Min Act: -0.0000

Data Index: 1401841 (The Pile)

Max Activating Token Index: 355

Text #4

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.2622. Min Act: -0.0000

Data Index: 1438600 (The Pile)

Max Activating Token Index: 788

Text #5

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.2436. Min Act: -0.0000

Data Index: 1977182 (The Pile)

Max Activating Token Index: 90

Text #6

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.2392. Min Act: -0.0000

Data Index: 374943 (The Pile)

Max Activating Token Index: 971

Text #7

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.2447. Min Act: -0.0000

Data Index: 205605 (The Pile)

Max Activating Token Index: 538

Text #8

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.2196. Min Act: -0.0000

Data Index: 554251 (The Pile)

Max Activating Token Index: 69

Text #9

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.2510. Min Act: -0.0000

Data Index: 632518 (The Pile)

Max Activating Token Index: 687

Text #10

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.2308. Min Act: -0.0000

Data Index: 611997 (The Pile)

Max Activating Token Index: 528

Text #11

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.2368. Min Act: -0.0000

Data Index: 451429 (The Pile)

Max Activating Token Index: 525

Text #12

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.2296. Min Act: -0.0000

Data Index: 1936425 (The Pile)

Max Activating Token Index: 857

Text #13

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.2396. Min Act: -0.0000

Data Index: 1479323 (The Pile)

Max Activating Token Index: 714

Text #14

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.2293. Min Act: -0.0000

Data Index: 1451167 (The Pile)

Max Activating Token Index: 565

Text #15

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.2291. Min Act: -0.0000

Data Index: 353375 (The Pile)

Max Activating Token Index: 368

Text #16

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.2206. Min Act: -0.0000

Data Index: 559169 (The Pile)

Max Activating Token Index: 111

Text #17

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.2175. Min Act: -0.0000

Data Index: 1616286 (The Pile)

Max Activating Token Index: 892

Text #18

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.2185. Min Act: -0.0000

Data Index: 1960663 (The Pile)

Max Activating Token Index: 785

Text #19

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.2184. Min Act: -0.0000

Data Index: 392880 (The Pile)

Max Activating Token Index: 331