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

Dataset: The Pile

Neuron 1670 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: 1.9401. Min Range: -1.9401

Max Act: 1.9401. Min Act: -0.0000

Data Index: 365090 (The Pile)

Max Activating Token Index: 242

Text #1

Max Range: 1.9401. Min Range: -1.9401

Max Act: 1.9319. Min Act: -0.0000

Data Index: 703145 (The Pile)

Max Activating Token Index: 175

Text #2

Max Range: 1.9401. Min Range: -1.9401

Max Act: 1.3930. Min Act: -0.0000

Data Index: 596610 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 1.9401. Min Range: -1.9401

Max Act: 1.4406. Min Act: -0.0000

Data Index: 1486776 (The Pile)

Max Activating Token Index: 339

Text #4

Max Range: 1.9401. Min Range: -1.9401

Max Act: 1.5732. Min Act: -0.0000

Data Index: 1226791 (The Pile)

Max Activating Token Index: 906

Text #5

Max Range: 1.9401. Min Range: -1.9401

Max Act: 1.4025. Min Act: -0.0000

Data Index: 1246228 (The Pile)

Max Activating Token Index: 996

Text #6

Max Range: 1.9401. Min Range: -1.9401

Max Act: 1.5133. Min Act: -0.0000

Data Index: 96820 (The Pile)

Max Activating Token Index: 287

Text #7

Max Range: 1.9401. Min Range: -1.9401

Max Act: 1.3246. Min Act: -0.0000

Data Index: 1359057 (The Pile)

Max Activating Token Index: 959

Text #8

Max Range: 1.9401. Min Range: -1.9401

Max Act: 1.3370. Min Act: -0.0000

Data Index: 1638353 (The Pile)

Max Activating Token Index: 891

Text #9

Max Range: 1.9401. Min Range: -1.9401

Max Act: 1.3399. Min Act: -0.0000

Data Index: 386195 (The Pile)

Max Activating Token Index: 308

Text #10

Max Range: 1.9401. Min Range: -1.9401

Max Act: 1.2564. Min Act: -0.0000

Data Index: 652553 (The Pile)

Max Activating Token Index: 846

Text #11

Max Range: 1.9401. Min Range: -1.9401

Max Act: 1.3732. Min Act: -0.0000

Data Index: 819681 (The Pile)

Max Activating Token Index: 697

Text #12

Max Range: 1.9401. Min Range: -1.9401

Max Act: 1.2180. Min Act: -0.0000

Data Index: 1296318 (The Pile)

Max Activating Token Index: 404

Text #13

Max Range: 1.9401. Min Range: -1.9401

Max Act: 1.2936. Min Act: -0.0000

Data Index: 1916993 (The Pile)

Max Activating Token Index: 476

Text #14

Max Range: 1.9401. Min Range: -1.9401

Max Act: 1.2376. Min Act: -0.0000

Data Index: 823227 (The Pile)

Max Activating Token Index: 463

Text #15

Max Range: 1.9401. Min Range: -1.9401

Max Act: 1.1212. Min Act: -0.0000

Data Index: 450177 (The Pile)

Max Activating Token Index: 962

Text #16

Max Range: 1.9401. Min Range: -1.9401

Max Act: 1.1362. Min Act: -0.0000

Data Index: 572380 (The Pile)

Max Activating Token Index: 294

Text #17

Max Range: 1.9401. Min Range: -1.9401

Max Act: 1.1847. Min Act: -0.0000

Data Index: 942815 (The Pile)

Max Activating Token Index: 331

Text #18

Max Range: 1.9401. Min Range: -1.9401

Max Act: 1.0613. Min Act: -0.0000

Data Index: 11899 (The Pile)

Max Activating Token Index: 584

Text #19

Max Range: 1.9401. Min Range: -1.9401

Max Act: 1.0185. Min Act: -0.0000

Data Index: 1495282 (The Pile)

Max Activating Token Index: 951