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

Dataset: The Pile

Neuron 4643 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0367. Min Act: -0.0000

Data Index: 1604136 (The Pile)

Max Activating Token Index: 318

Text #1

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0363. Min Act: -0.0000

Data Index: 1932273 (The Pile)

Max Activating Token Index: 398

Text #2

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0344. Min Act: -0.0000

Data Index: 1018883 (The Pile)

Max Activating Token Index: 253

Text #3

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0324. Min Act: -0.0000

Data Index: 1483905 (The Pile)

Max Activating Token Index: 251

Text #4

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0334. Min Act: -0.0000

Data Index: 1395416 (The Pile)

Max Activating Token Index: 467

Text #5

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0329. Min Act: -0.0000

Data Index: 401085 (The Pile)

Max Activating Token Index: 616

Text #6

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0329. Min Act: 0.0000

Data Index: 702867 (The Pile)

Max Activating Token Index: 715

Text #7

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0326. Min Act: -0.0000

Data Index: 522130 (The Pile)

Max Activating Token Index: 256

Text #8

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0322. Min Act: 0.0000

Data Index: 758071 (The Pile)

Max Activating Token Index: 428

Text #9

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0308. Min Act: -0.0000

Data Index: 854553 (The Pile)

Max Activating Token Index: 140

Text #10

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0327. Min Act: 0.0000

Data Index: 527767 (The Pile)

Max Activating Token Index: 259

Text #11

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0309. Min Act: -0.0000

Data Index: 695565 (The Pile)

Max Activating Token Index: 465

Text #12

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0314. Min Act: -0.0000

Data Index: 228204 (The Pile)

Max Activating Token Index: 409

Text #13

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0307. Min Act: 0.0000

Data Index: 340750 (The Pile)

Max Activating Token Index: 21

Text #14

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0313. Min Act: 0.0000

Data Index: 882648 (The Pile)

Max Activating Token Index: 985

Text #15

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0310. Min Act: 0.0000

Data Index: 1842328 (The Pile)

Max Activating Token Index: 98

Text #16

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0316. Min Act: 0.0000

Data Index: 1378922 (The Pile)

Max Activating Token Index: 810

Text #17

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0304. Min Act: -0.0000

Data Index: 385053 (The Pile)

Max Activating Token Index: 67

Text #18

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0293. Min Act: -0.0000

Data Index: 1918615 (The Pile)

Max Activating Token Index: 579

Text #19

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0302. Min Act: -0.0000

Data Index: 1331959 (The Pile)

Max Activating Token Index: 369