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

Dataset: The Pile

Neuron 3633 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.3897. Min Act: -0.0000

Data Index: 295583 (The Pile)

Max Activating Token Index: 91

Text #1

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.3731. Min Act: -0.0000

Data Index: 140532 (The Pile)

Max Activating Token Index: 336

Text #2

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.3911. Min Act: -0.0000

Data Index: 1404085 (The Pile)

Max Activating Token Index: 630

Text #3

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.3690. Min Act: -0.0000

Data Index: 538966 (The Pile)

Max Activating Token Index: 885

Text #4

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.3645. Min Act: -0.0000

Data Index: 1940205 (The Pile)

Max Activating Token Index: 999

Text #5

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.3573. Min Act: -0.0000

Data Index: 488399 (The Pile)

Max Activating Token Index: 132

Text #6

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.3404. Min Act: -0.0000

Data Index: 18478 (The Pile)

Max Activating Token Index: 58

Text #7

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.3299. Min Act: -0.0000

Data Index: 570581 (The Pile)

Max Activating Token Index: 953

Text #8

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.3531. Min Act: -0.0000

Data Index: 1095472 (The Pile)

Max Activating Token Index: 114

Text #9

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.3423. Min Act: -0.0000

Data Index: 1780387 (The Pile)

Max Activating Token Index: 927

Text #10

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.3379. Min Act: -0.0000

Data Index: 1240956 (The Pile)

Max Activating Token Index: 144

Text #11

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.3371. Min Act: -0.0000

Data Index: 439849 (The Pile)

Max Activating Token Index: 357

Text #12

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.3230. Min Act: -0.0000

Data Index: 1985568 (The Pile)

Max Activating Token Index: 795

Text #13

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.3309. Min Act: -0.0000

Data Index: 1602419 (The Pile)

Max Activating Token Index: 251

Text #14

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.3325. Min Act: -0.0000

Data Index: 1461876 (The Pile)

Max Activating Token Index: 225

Text #15

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.3513. Min Act: -0.0000

Data Index: 244295 (The Pile)

Max Activating Token Index: 34

Text #16

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.3290. Min Act: -0.0000

Data Index: 1199548 (The Pile)

Max Activating Token Index: 197

Text #17

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.3143. Min Act: -0.0000

Data Index: 70126 (The Pile)

Max Activating Token Index: 189

Text #18

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.3243. Min Act: -0.0000

Data Index: 1019330 (The Pile)

Max Activating Token Index: 742

Text #19

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.3136. Min Act: -0.0000

Data Index: 1378980 (The Pile)

Max Activating Token Index: 755