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

Dataset: The Pile

Neuron 2855 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9359. Min Range: -1.9359

Max Act: 1.9359. Min Act: -0.0000

Data Index: 1947244 (The Pile)

Max Activating Token Index: 660

Text #1

Max Range: 1.9359. Min Range: -1.9359

Max Act: 1.6518. Min Act: -0.0000

Data Index: 15233 (The Pile)

Max Activating Token Index: 466

Text #2

Max Range: 1.9359. Min Range: -1.9359

Max Act: 1.2924. Min Act: -0.0000

Data Index: 241958 (The Pile)

Max Activating Token Index: 306

Text #3

Max Range: 1.9359. Min Range: -1.9359

Max Act: 1.3312. Min Act: -0.0000

Data Index: 1228375 (The Pile)

Max Activating Token Index: 395

Text #4

Max Range: 1.9359. Min Range: -1.9359

Max Act: 1.3011. Min Act: -0.0000

Data Index: 1055280 (The Pile)

Max Activating Token Index: 542

Text #5

Max Range: 1.9359. Min Range: -1.9359

Max Act: 1.0604. Min Act: -0.0000

Data Index: 1940432 (The Pile)

Max Activating Token Index: 661

Text #6

Max Range: 1.9359. Min Range: -1.9359

Max Act: 1.0144. Min Act: -0.0000

Data Index: 665386 (The Pile)

Max Activating Token Index: 375

Text #7

Max Range: 1.9359. Min Range: -1.9359

Max Act: 1.0842. Min Act: -0.0000

Data Index: 888469 (The Pile)

Max Activating Token Index: 516

Text #8

Max Range: 1.9359. Min Range: -1.9359

Max Act: 1.0277. Min Act: -0.0000

Data Index: 962929 (The Pile)

Max Activating Token Index: 584

Text #9

Max Range: 1.9359. Min Range: -1.9359

Max Act: 1.1543. Min Act: -0.0000

Data Index: 619347 (The Pile)

Max Activating Token Index: 631

Text #10

Max Range: 1.9359. Min Range: -1.9359

Max Act: 1.1259. Min Act: -0.0000

Data Index: 1312406 (The Pile)

Max Activating Token Index: 239

Text #11

Max Range: 1.9359. Min Range: -1.9359

Max Act: 0.9644. Min Act: 0.0000

Data Index: 304150 (The Pile)

Max Activating Token Index: 814

Text #12

Max Range: 1.9359. Min Range: -1.9359

Max Act: 0.9356. Min Act: -0.0000

Data Index: 471630 (The Pile)

Max Activating Token Index: 500

Text #13

Max Range: 1.9359. Min Range: -1.9359

Max Act: 0.9889. Min Act: -0.0000

Data Index: 1333169 (The Pile)

Max Activating Token Index: 405

Text #14

Max Range: 1.9359. Min Range: -1.9359

Max Act: 1.0181. Min Act: -0.0000

Data Index: 58097 (The Pile)

Max Activating Token Index: 454

Text #15

Max Range: 1.9359. Min Range: -1.9359

Max Act: 1.0093. Min Act: -0.0000

Data Index: 1892875 (The Pile)

Max Activating Token Index: 510

Text #16

Max Range: 1.9359. Min Range: -1.9359

Max Act: 1.0223. Min Act: -0.0000

Data Index: 1906215 (The Pile)

Max Activating Token Index: 592

Text #17

Max Range: 1.9359. Min Range: -1.9359

Max Act: 0.9415. Min Act: -0.0000

Data Index: 138173 (The Pile)

Max Activating Token Index: 961

Text #18

Max Range: 1.9359. Min Range: -1.9359

Max Act: 0.9262. Min Act: -0.0000

Data Index: 414955 (The Pile)

Max Activating Token Index: 380

Text #19

Max Range: 1.9359. Min Range: -1.9359

Max Act: 1.0810. Min Act: -0.0000

Data Index: 940955 (The Pile)

Max Activating Token Index: 610