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

Dataset: The Pile

Neuron 1302 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: 1.2756. Min Range: -1.2756

Max Act: 1.2756. Min Act: -0.0000

Data Index: 368828 (The Pile)

Max Activating Token Index: 782

Text #1

Max Range: 1.2756. Min Range: -1.2756

Max Act: 0.9453. Min Act: -0.0000

Data Index: 85410 (The Pile)

Max Activating Token Index: 375

Text #2

Max Range: 1.2756. Min Range: -1.2756

Max Act: 0.8582. Min Act: -0.0000

Data Index: 1211249 (The Pile)

Max Activating Token Index: 242

Text #3

Max Range: 1.2756. Min Range: -1.2756

Max Act: 0.8793. Min Act: -0.0000

Data Index: 1987267 (The Pile)

Max Activating Token Index: 316

Text #4

Max Range: 1.2756. Min Range: -1.2756

Max Act: 0.8183. Min Act: -0.0000

Data Index: 1691705 (The Pile)

Max Activating Token Index: 899

Text #5

Max Range: 1.2756. Min Range: -1.2756

Max Act: 0.8137. Min Act: -0.0000

Data Index: 1345781 (The Pile)

Max Activating Token Index: 676

Text #6

Max Range: 1.2756. Min Range: -1.2756

Max Act: 0.8673. Min Act: -0.0000

Data Index: 1932672 (The Pile)

Max Activating Token Index: 1015

Text #7

Max Range: 1.2756. Min Range: -1.2756

Max Act: 0.8337. Min Act: 0.0000

Data Index: 1367894 (The Pile)

Max Activating Token Index: 307

Text #8

Max Range: 1.2756. Min Range: -1.2756

Max Act: 0.8175. Min Act: -0.0000

Data Index: 365956 (The Pile)

Max Activating Token Index: 475

Text #9

Max Range: 1.2756. Min Range: -1.2756

Max Act: 0.7764. Min Act: -0.0000

Data Index: 222918 (The Pile)

Max Activating Token Index: 102

Text #10

Max Range: 1.2756. Min Range: -1.2756

Max Act: 0.7777. Min Act: -0.0000

Data Index: 1888827 (The Pile)

Max Activating Token Index: 852

Text #11

Max Range: 1.2756. Min Range: -1.2756

Max Act: 0.7742. Min Act: 0.0000

Data Index: 141987 (The Pile)

Max Activating Token Index: 185

Text #12

Max Range: 1.2756. Min Range: -1.2756

Max Act: 0.7698. Min Act: -0.0000

Data Index: 1600904 (The Pile)

Max Activating Token Index: 978

Text #13

Max Range: 1.2756. Min Range: -1.2756

Max Act: 0.8009. Min Act: -0.0000

Data Index: 542031 (The Pile)

Max Activating Token Index: 295

Text #14

Max Range: 1.2756. Min Range: -1.2756

Max Act: 0.7910. Min Act: -0.0000

Data Index: 881700 (The Pile)

Max Activating Token Index: 895

Text #15

Max Range: 1.2756. Min Range: -1.2756

Max Act: 0.7547. Min Act: -0.0000

Data Index: 482956 (The Pile)

Max Activating Token Index: 390

Text #16

Max Range: 1.2756. Min Range: -1.2756

Max Act: 0.7997. Min Act: -0.0000

Data Index: 489420 (The Pile)

Max Activating Token Index: 389

Text #17

Max Range: 1.2756. Min Range: -1.2756

Max Act: 0.7955. Min Act: -0.0000

Data Index: 1886746 (The Pile)

Max Activating Token Index: 482

Text #18

Max Range: 1.2756. Min Range: -1.2756

Max Act: 0.7438. Min Act: -0.0000

Data Index: 713984 (The Pile)

Max Activating Token Index: 513

Text #19

Max Range: 1.2756. Min Range: -1.2756

Max Act: 0.7686. Min Act: -0.0000

Data Index: 654115 (The Pile)

Max Activating Token Index: 77