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

Dataset: The Pile

Neuron 1619 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.6227. Min Act: -0.0000

Data Index: 21130 (The Pile)

Max Activating Token Index: 26

Text #1

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.6310. Min Act: -0.0000

Data Index: 675139 (The Pile)

Max Activating Token Index: 690

Text #2

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.4515. Min Act: -0.0000

Data Index: 1642028 (The Pile)

Max Activating Token Index: 970

Text #3

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.3752. Min Act: -0.0000

Data Index: 1719979 (The Pile)

Max Activating Token Index: 581

Text #4

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.4203. Min Act: -0.0000

Data Index: 226339 (The Pile)

Max Activating Token Index: 96

Text #5

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.3967. Min Act: -0.0000

Data Index: 1997109 (The Pile)

Max Activating Token Index: 820

Text #6

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.3869. Min Act: -0.0000

Data Index: 1699029 (The Pile)

Max Activating Token Index: 41

Text #7

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.3123. Min Act: -0.0000

Data Index: 517036 (The Pile)

Max Activating Token Index: 428

Text #8

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.3343. Min Act: -0.0000

Data Index: 831153 (The Pile)

Max Activating Token Index: 648

Text #9

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.3044. Min Act: -0.0000

Data Index: 1934967 (The Pile)

Max Activating Token Index: 68

Text #10

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.2937. Min Act: -0.0000

Data Index: 218835 (The Pile)

Max Activating Token Index: 132

Text #11

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.2955. Min Act: -0.0000

Data Index: 339946 (The Pile)

Max Activating Token Index: 205

Text #12

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.2423. Min Act: -0.0000

Data Index: 1975517 (The Pile)

Max Activating Token Index: 787

Text #13

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.2582. Min Act: -0.0000

Data Index: 1371847 (The Pile)

Max Activating Token Index: 899

Text #14

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.1756. Min Act: -0.0000

Data Index: 461397 (The Pile)

Max Activating Token Index: 334

Text #15

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.2452. Min Act: -0.0000

Data Index: 1192515 (The Pile)

Max Activating Token Index: 741

Text #16

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.2294. Min Act: -0.0000

Data Index: 154894 (The Pile)

Max Activating Token Index: 960

Text #17

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.1043. Min Act: -0.0000

Data Index: 654031 (The Pile)

Max Activating Token Index: 603

Text #18

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.1880. Min Act: -0.0000

Data Index: 1335835 (The Pile)

Max Activating Token Index: 660

Text #19

Max Range: 1.6310. Min Range: -1.6310

Max Act: 1.2191. Min Act: -0.0000

Data Index: 1568335 (The Pile)

Max Activating Token Index: 594