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

Dataset: The Pile

Neuron 2624 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: 0.2764. Min Range: -0.2764

Max Act: 0.2578. Min Act: -0.0000

Data Index: 744332 (The Pile)

Max Activating Token Index: 737

Text #1

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.2487. Min Act: -0.0000

Data Index: 1563474 (The Pile)

Max Activating Token Index: 986

Text #2

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.2764. Min Act: -0.0000

Data Index: 1948257 (The Pile)

Max Activating Token Index: 565

Text #3

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.2687. Min Act: -0.0000

Data Index: 1873122 (The Pile)

Max Activating Token Index: 156

Text #4

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.2305. Min Act: -0.0000

Data Index: 1985337 (The Pile)

Max Activating Token Index: 332

Text #5

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.2748. Min Act: -0.0000

Data Index: 132118 (The Pile)

Max Activating Token Index: 484

Text #6

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.2302. Min Act: -0.0000

Data Index: 1671390 (The Pile)

Max Activating Token Index: 1017

Text #7

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.2697. Min Act: -0.0000

Data Index: 1219373 (The Pile)

Max Activating Token Index: 983

Text #8

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.2042. Min Act: -0.0000

Data Index: 821878 (The Pile)

Max Activating Token Index: 990

Text #9

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.2453. Min Act: -0.0000

Data Index: 1200377 (The Pile)

Max Activating Token Index: 524

Text #10

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.2592. Min Act: -0.0000

Data Index: 999688 (The Pile)

Max Activating Token Index: 652

Text #11

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.2092. Min Act: -0.0000

Data Index: 1057318 (The Pile)

Max Activating Token Index: 573

Text #12

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.1919. Min Act: -0.0000

Data Index: 776867 (The Pile)

Max Activating Token Index: 484

Text #13

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.2432. Min Act: -0.0000

Data Index: 1828015 (The Pile)

Max Activating Token Index: 764

Text #14

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.2085. Min Act: -0.0000

Data Index: 1751030 (The Pile)

Max Activating Token Index: 801

Text #15

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.2312. Min Act: -0.0000

Data Index: 1656945 (The Pile)

Max Activating Token Index: 95

Text #16

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.1921. Min Act: -0.0000

Data Index: 465829 (The Pile)

Max Activating Token Index: 429

Text #17

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.2181. Min Act: -0.0000

Data Index: 209800 (The Pile)

Max Activating Token Index: 823

Text #18

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.2101. Min Act: -0.0000

Data Index: 1506028 (The Pile)

Max Activating Token Index: 625

Text #19

Max Range: 0.2764. Min Range: -0.2764

Max Act: 0.1952. Min Act: -0.0000

Data Index: 532552 (The Pile)

Max Activating Token Index: 566