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

Dataset: The Pile

Neuron 3522 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.8150. Min Act: -0.0000

Data Index: 1498248 (The Pile)

Max Activating Token Index: 768

Text #1

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.8208. Min Act: -0.0000

Data Index: 847586 (The Pile)

Max Activating Token Index: 415

Text #2

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.7321. Min Act: -0.0000

Data Index: 1690242 (The Pile)

Max Activating Token Index: 760

Text #3

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.5873. Min Act: -0.0000

Data Index: 1445064 (The Pile)

Max Activating Token Index: 894

Text #4

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.6101. Min Act: -0.0000

Data Index: 17678 (The Pile)

Max Activating Token Index: 321

Text #5

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.5969. Min Act: -0.0000

Data Index: 152287 (The Pile)

Max Activating Token Index: 518

Text #6

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.5257. Min Act: -0.0000

Data Index: 1252361 (The Pile)

Max Activating Token Index: 955

Text #7

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.5137. Min Act: -0.0000

Data Index: 790371 (The Pile)

Max Activating Token Index: 271

Text #8

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.5107. Min Act: -0.0000

Data Index: 668270 (The Pile)

Max Activating Token Index: 289

Text #9

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.4210. Min Act: 0.0000

Data Index: 941521 (The Pile)

Max Activating Token Index: 741

Text #10

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.5388. Min Act: -0.0000

Data Index: 1579449 (The Pile)

Max Activating Token Index: 671

Text #11

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.4661. Min Act: -0.0000

Data Index: 1815565 (The Pile)

Max Activating Token Index: 90

Text #12

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.4470. Min Act: -0.0000

Data Index: 1441840 (The Pile)

Max Activating Token Index: 722

Text #13

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.4111. Min Act: -0.0000

Data Index: 1484873 (The Pile)

Max Activating Token Index: 90

Text #14

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.4324. Min Act: -0.0000

Data Index: 1707181 (The Pile)

Max Activating Token Index: 346

Text #15

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.4462. Min Act: -0.0000

Data Index: 1566237 (The Pile)

Max Activating Token Index: 448

Text #16

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.4627. Min Act: -0.0000

Data Index: 232368 (The Pile)

Max Activating Token Index: 571

Text #17

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.4928. Min Act: -0.0000

Data Index: 792219 (The Pile)

Max Activating Token Index: 716

Text #18

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1635011 (The Pile)

Max Activating Token Index: 813

Text #19

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.4434. Min Act: -0.0000

Data Index: 1167308 (The Pile)

Max Activating Token Index: 512