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

Dataset: The Pile

Neuron 1561 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.5453. Min Act: -0.0000

Data Index: 1398967 (The Pile)

Max Activating Token Index: 401

Text #1

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.3973. Min Act: -0.0000

Data Index: 1814480 (The Pile)

Max Activating Token Index: 62

Text #2

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.2907. Min Act: -0.0000

Data Index: 1485701 (The Pile)

Max Activating Token Index: 893

Text #3

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.3664. Min Act: -0.0000

Data Index: 1388111 (The Pile)

Max Activating Token Index: 142

Text #4

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.4425. Min Act: -0.0000

Data Index: 1891108 (The Pile)

Max Activating Token Index: 259

Text #5

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.3263. Min Act: -0.0000

Data Index: 1968290 (The Pile)

Max Activating Token Index: 101

Text #6

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.2664. Min Act: -0.0000

Data Index: 970144 (The Pile)

Max Activating Token Index: 851

Text #7

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.3117. Min Act: -0.0000

Data Index: 62142 (The Pile)

Max Activating Token Index: 998

Text #8

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.3098. Min Act: -0.0000

Data Index: 1110179 (The Pile)

Max Activating Token Index: 545

Text #9

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.2898. Min Act: -0.0000

Data Index: 1556698 (The Pile)

Max Activating Token Index: 452

Text #10

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.2854. Min Act: -0.0000

Data Index: 1107699 (The Pile)

Max Activating Token Index: 281

Text #11

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.2838. Min Act: -0.0000

Data Index: 511300 (The Pile)

Max Activating Token Index: 611

Text #12

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.2799. Min Act: -0.0000

Data Index: 1138842 (The Pile)

Max Activating Token Index: 277

Text #13

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.2720. Min Act: -0.0000

Data Index: 482659 (The Pile)

Max Activating Token Index: 739

Text #14

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.2701. Min Act: -0.0000

Data Index: 202551 (The Pile)

Max Activating Token Index: 322

Text #15

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.3415. Min Act: -0.0000

Data Index: 1487732 (The Pile)

Max Activating Token Index: 412

Text #16

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.2635. Min Act: -0.0000

Data Index: 310065 (The Pile)

Max Activating Token Index: 388

Text #17

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.2557. Min Act: -0.0000

Data Index: 1132107 (The Pile)

Max Activating Token Index: 248

Text #18

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.2501. Min Act: -0.0000

Data Index: 434428 (The Pile)

Max Activating Token Index: 31

Text #19

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.3362. Min Act: -0.0000

Data Index: 696296 (The Pile)

Max Activating Token Index: 959