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

Dataset: The Pile

Neuron 2015 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.4138. Min Act: -0.0000

Data Index: 1242980 (The Pile)

Max Activating Token Index: 442

Text #1

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.2973. Min Act: -0.0000

Data Index: 1871030 (The Pile)

Max Activating Token Index: 854

Text #2

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.3651. Min Act: -0.0000

Data Index: 136463 (The Pile)

Max Activating Token Index: 158

Text #3

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.3084. Min Act: -0.0000

Data Index: 1224513 (The Pile)

Max Activating Token Index: 318

Text #4

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.2598. Min Act: -0.0000

Data Index: 190335 (The Pile)

Max Activating Token Index: 282

Text #5

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.2532. Min Act: -0.0000

Data Index: 1663105 (The Pile)

Max Activating Token Index: 900

Text #6

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.2719. Min Act: -0.0000

Data Index: 172755 (The Pile)

Max Activating Token Index: 378

Text #7

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.2579. Min Act: -0.0000

Data Index: 919855 (The Pile)

Max Activating Token Index: 936

Text #8

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.2234. Min Act: -0.0000

Data Index: 145698 (The Pile)

Max Activating Token Index: 149

Text #9

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.2947. Min Act: -0.0000

Data Index: 433935 (The Pile)

Max Activating Token Index: 137

Text #10

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.2468. Min Act: -0.0000

Data Index: 1708639 (The Pile)

Max Activating Token Index: 729

Text #11

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.1798. Min Act: -0.0000

Data Index: 1888042 (The Pile)

Max Activating Token Index: 860

Text #12

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.1707. Min Act: -0.0000

Data Index: 1331321 (The Pile)

Max Activating Token Index: 517

Text #13

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.1937. Min Act: -0.0000

Data Index: 244290 (The Pile)

Max Activating Token Index: 1004

Text #14

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.2393. Min Act: -0.0000

Data Index: 1220064 (The Pile)

Max Activating Token Index: 617

Text #15

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.2024. Min Act: -0.0000

Data Index: 665960 (The Pile)

Max Activating Token Index: 508

Text #16

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.1890. Min Act: -0.0000

Data Index: 404407 (The Pile)

Max Activating Token Index: 238

Text #17

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.2117. Min Act: -0.0000

Data Index: 69899 (The Pile)

Max Activating Token Index: 636

Text #18

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.1661. Min Act: -0.0000

Data Index: 1284530 (The Pile)

Max Activating Token Index: 66

Text #19

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.1629. Min Act: -0.0000

Data Index: 1027502 (The Pile)

Max Activating Token Index: 804