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

Dataset: The Pile

Neuron 948 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: 1.2970. Min Range: -1.2970

Max Act: 1.2970. Min Act: -0.0000

Data Index: 1399872 (The Pile)

Max Activating Token Index: 30

Text #1

Max Range: 1.2970. Min Range: -1.2970

Max Act: 1.1256. Min Act: -0.0000

Data Index: 655160 (The Pile)

Max Activating Token Index: 187

Text #2

Max Range: 1.2970. Min Range: -1.2970

Max Act: 1.0532. Min Act: -0.0000

Data Index: 1423696 (The Pile)

Max Activating Token Index: 979

Text #3

Max Range: 1.2970. Min Range: -1.2970

Max Act: 1.0436. Min Act: -0.0000

Data Index: 1441067 (The Pile)

Max Activating Token Index: 796

Text #4

Max Range: 1.2970. Min Range: -1.2970

Max Act: 1.0390. Min Act: -0.0000

Data Index: 589392 (The Pile)

Max Activating Token Index: 5

Text #5

Max Range: 1.2970. Min Range: -1.2970

Max Act: 1.0518. Min Act: -0.0000

Data Index: 1233326 (The Pile)

Max Activating Token Index: 241

Text #6

Max Range: 1.2970. Min Range: -1.2970

Max Act: 1.0067. Min Act: -0.0000

Data Index: 680572 (The Pile)

Max Activating Token Index: 470

Text #7

Max Range: 1.2970. Min Range: -1.2970

Max Act: 0.9740. Min Act: -0.0000

Data Index: 1813412 (The Pile)

Max Activating Token Index: 428

Text #8

Max Range: 1.2970. Min Range: -1.2970

Max Act: 0.9376. Min Act: -0.0000

Data Index: 282496 (The Pile)

Max Activating Token Index: 44

Text #9

Max Range: 1.2970. Min Range: -1.2970

Max Act: 0.9735. Min Act: -0.0000

Data Index: 225078 (The Pile)

Max Activating Token Index: 854

Text #10

Max Range: 1.2970. Min Range: -1.2970

Max Act: 0.9359. Min Act: -0.0000

Data Index: 1721463 (The Pile)

Max Activating Token Index: 361

Text #11

Max Range: 1.2970. Min Range: -1.2970

Max Act: 0.9934. Min Act: -0.0000

Data Index: 134338 (The Pile)

Max Activating Token Index: 382

Text #12

Max Range: 1.2970. Min Range: -1.2970

Max Act: 0.9510. Min Act: -0.0000

Data Index: 701717 (The Pile)

Max Activating Token Index: 164

Text #13

Max Range: 1.2970. Min Range: -1.2970

Max Act: 0.8850. Min Act: -0.0000

Data Index: 1962912 (The Pile)

Max Activating Token Index: 761

Text #14

Max Range: 1.2970. Min Range: -1.2970

Max Act: 1.0373. Min Act: -0.0000

Data Index: 1933436 (The Pile)

Max Activating Token Index: 1015

Text #15

Max Range: 1.2970. Min Range: -1.2970

Max Act: 0.9427. Min Act: -0.0000

Data Index: 103697 (The Pile)

Max Activating Token Index: 178

Text #16

Max Range: 1.2970. Min Range: -1.2970

Max Act: 0.9275. Min Act: -0.0000

Data Index: 1302781 (The Pile)

Max Activating Token Index: 421

Text #17

Max Range: 1.2970. Min Range: -1.2970

Max Act: 0.9338. Min Act: -0.0000

Data Index: 624389 (The Pile)

Max Activating Token Index: 137

Text #18

Max Range: 1.2970. Min Range: -1.2970

Max Act: 0.9228. Min Act: -0.0000

Data Index: 356467 (The Pile)

Max Activating Token Index: 686

Text #19

Max Range: 1.2970. Min Range: -1.2970

Max Act: 0.9474. Min Act: -0.0000

Data Index: 728048 (The Pile)

Max Activating Token Index: 626