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

Dataset: The Pile

Neuron 2786 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.7050. Min Act: -0.0000

Data Index: 325915 (The Pile)

Max Activating Token Index: 847

Text #1

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.6747. Min Act: -0.0000

Data Index: 1898722 (The Pile)

Max Activating Token Index: 538

Text #2

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.7185. Min Act: -0.0000

Data Index: 19437 (The Pile)

Max Activating Token Index: 704

Text #3

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.7030. Min Act: -0.0000

Data Index: 1174556 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.6903. Min Act: -0.0000

Data Index: 566975 (The Pile)

Max Activating Token Index: 792

Text #5

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.6542. Min Act: -0.0000

Data Index: 75986 (The Pile)

Max Activating Token Index: 396

Text #6

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.7306. Min Act: -0.0000

Data Index: 1903839 (The Pile)

Max Activating Token Index: 576

Text #7

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.6332. Min Act: -0.0000

Data Index: 408393 (The Pile)

Max Activating Token Index: 1013

Text #8

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.6108. Min Act: 0.0000

Data Index: 358844 (The Pile)

Max Activating Token Index: 300

Text #9

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.6920. Min Act: -0.0000

Data Index: 498757 (The Pile)

Max Activating Token Index: 511

Text #10

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.6212. Min Act: -0.0000

Data Index: 760448 (The Pile)

Max Activating Token Index: 838

Text #11

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.6442. Min Act: -0.0000

Data Index: 108228 (The Pile)

Max Activating Token Index: 619

Text #12

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.6134. Min Act: -0.0000

Data Index: 616455 (The Pile)

Max Activating Token Index: 784

Text #13

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.6306. Min Act: -0.0000

Data Index: 1348127 (The Pile)

Max Activating Token Index: 1004

Text #14

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.6094. Min Act: -0.0000

Data Index: 1772950 (The Pile)

Max Activating Token Index: 273

Text #15

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5342. Min Act: -0.0000

Data Index: 387987 (The Pile)

Max Activating Token Index: 377

Text #16

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.6397. Min Act: -0.0000

Data Index: 223545 (The Pile)

Max Activating Token Index: 676

Text #17

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.6313. Min Act: -0.0000

Data Index: 21535 (The Pile)

Max Activating Token Index: 571

Text #18

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.4897. Min Act: -0.0000

Data Index: 1172116 (The Pile)

Max Activating Token Index: 658

Text #19

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5851. Min Act: 0.0000

Data Index: 361582 (The Pile)

Max Activating Token Index: 130