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

Dataset: The Pile

Neuron 540 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: 0.9561. Min Range: -0.9561

Max Act: 0.9561. Min Act: -0.0000

Data Index: 528074 (The Pile)

Max Activating Token Index: 455

Text #1

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.9315. Min Act: -0.0000

Data Index: 1925727 (The Pile)

Max Activating Token Index: 534

Text #2

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8879. Min Act: -0.0000

Data Index: 1400622 (The Pile)

Max Activating Token Index: 766

Text #3

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.9289. Min Act: -0.0000

Data Index: 1828578 (The Pile)

Max Activating Token Index: 433

Text #4

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8677. Min Act: -0.0000

Data Index: 817803 (The Pile)

Max Activating Token Index: 25

Text #5

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8910. Min Act: -0.0000

Data Index: 664982 (The Pile)

Max Activating Token Index: 1002

Text #6

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8268. Min Act: -0.0000

Data Index: 1804611 (The Pile)

Max Activating Token Index: 917

Text #7

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8729. Min Act: -0.0000

Data Index: 957665 (The Pile)

Max Activating Token Index: 251

Text #8

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8215. Min Act: -0.0000

Data Index: 1173706 (The Pile)

Max Activating Token Index: 662

Text #9

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8825. Min Act: -0.0000

Data Index: 388131 (The Pile)

Max Activating Token Index: 397

Text #10

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8418. Min Act: -0.0000

Data Index: 789112 (The Pile)

Max Activating Token Index: 468

Text #11

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.7907. Min Act: -0.0000

Data Index: 551078 (The Pile)

Max Activating Token Index: 670

Text #12

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8386. Min Act: -0.0000

Data Index: 680163 (The Pile)

Max Activating Token Index: 276

Text #13

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8369. Min Act: -0.0000

Data Index: 1003370 (The Pile)

Max Activating Token Index: 986

Text #14

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8539. Min Act: -0.0000

Data Index: 1532891 (The Pile)

Max Activating Token Index: 564

Text #15

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8479. Min Act: -0.0000

Data Index: 552658 (The Pile)

Max Activating Token Index: 314

Text #16

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.7904. Min Act: -0.0000

Data Index: 1947283 (The Pile)

Max Activating Token Index: 926

Text #17

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8105. Min Act: -0.0000

Data Index: 496180 (The Pile)

Max Activating Token Index: 363

Text #18

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.7857. Min Act: -0.0000

Data Index: 1307869 (The Pile)

Max Activating Token Index: 908

Text #19

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8094. Min Act: -0.0000

Data Index: 81563 (The Pile)

Max Activating Token Index: 707