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

Dataset: The Pile

Neuron 2940 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: 0.4816. Min Range: -0.4816

Max Act: 0.4816. Min Act: -0.0000

Data Index: 697619 (The Pile)

Max Activating Token Index: 79

Text #1

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.4585. Min Act: -0.0000

Data Index: 55912 (The Pile)

Max Activating Token Index: 552

Text #2

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.4318. Min Act: -0.0000

Data Index: 1531292 (The Pile)

Max Activating Token Index: 384

Text #3

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.4103. Min Act: -0.0000

Data Index: 532639 (The Pile)

Max Activating Token Index: 457

Text #4

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.4176. Min Act: -0.0000

Data Index: 1608078 (The Pile)

Max Activating Token Index: 212

Text #5

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.4148. Min Act: -0.0000

Data Index: 1778695 (The Pile)

Max Activating Token Index: 685

Text #6

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.4004. Min Act: -0.0000

Data Index: 1776885 (The Pile)

Max Activating Token Index: 122

Text #7

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.4001. Min Act: -0.0000

Data Index: 976948 (The Pile)

Max Activating Token Index: 415

Text #8

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3800. Min Act: -0.0000

Data Index: 1550755 (The Pile)

Max Activating Token Index: 349

Text #9

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.4058. Min Act: -0.0000

Data Index: 757534 (The Pile)

Max Activating Token Index: 729

Text #10

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3699. Min Act: -0.0000

Data Index: 1631992 (The Pile)

Max Activating Token Index: 132

Text #11

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3834. Min Act: -0.0000

Data Index: 1293547 (The Pile)

Max Activating Token Index: 18

Text #12

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3674. Min Act: -0.0000

Data Index: 318809 (The Pile)

Max Activating Token Index: 1010

Text #13

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3647. Min Act: -0.0000

Data Index: 697803 (The Pile)

Max Activating Token Index: 8

Text #14

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3733. Min Act: -0.0000

Data Index: 772438 (The Pile)

Max Activating Token Index: 241

Text #15

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3727. Min Act: -0.0000

Data Index: 1189238 (The Pile)

Max Activating Token Index: 958

Text #16

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3621. Min Act: -0.0000

Data Index: 320456 (The Pile)

Max Activating Token Index: 628

Text #17

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3682. Min Act: -0.0000

Data Index: 1601982 (The Pile)

Max Activating Token Index: 39

Text #18

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3539. Min Act: -0.0000

Data Index: 1579138 (The Pile)

Max Activating Token Index: 913

Text #19

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3373. Min Act: -0.0000

Data Index: 656513 (The Pile)

Max Activating Token Index: 714