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

Dataset: The Pile

Neuron 911 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.7203. Min Act: -0.0000

Data Index: 1365499 (The Pile)

Max Activating Token Index: 74

Text #1

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.6989. Min Act: -0.0000

Data Index: 1285282 (The Pile)

Max Activating Token Index: 106

Text #2

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.6530. Min Act: -0.0000

Data Index: 232711 (The Pile)

Max Activating Token Index: 677

Text #3

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.6947. Min Act: -0.0000

Data Index: 72910 (The Pile)

Max Activating Token Index: 288

Text #4

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.6740. Min Act: -0.0000

Data Index: 1899367 (The Pile)

Max Activating Token Index: 4

Text #5

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.6573. Min Act: -0.0000

Data Index: 1127332 (The Pile)

Max Activating Token Index: 48

Text #6

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.6413. Min Act: -0.0000

Data Index: 491934 (The Pile)

Max Activating Token Index: 203

Text #7

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.5741. Min Act: -0.0000

Data Index: 895451 (The Pile)

Max Activating Token Index: 39

Text #8

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.5878. Min Act: -0.0000

Data Index: 785521 (The Pile)

Max Activating Token Index: 784

Text #9

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.6388. Min Act: -0.0000

Data Index: 296529 (The Pile)

Max Activating Token Index: 425

Text #10

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.3950. Min Act: -0.0000

Data Index: 1491697 (The Pile)

Max Activating Token Index: 686

Text #11

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.5964. Min Act: -0.0000

Data Index: 741631 (The Pile)

Max Activating Token Index: 798

Text #12

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.6033. Min Act: -0.0000

Data Index: 1034288 (The Pile)

Max Activating Token Index: 454

Text #13

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.5937. Min Act: -0.0000

Data Index: 1065645 (The Pile)

Max Activating Token Index: 354

Text #14

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.5403. Min Act: -0.0000

Data Index: 1516314 (The Pile)

Max Activating Token Index: 169

Text #15

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.6349. Min Act: -0.0000

Data Index: 539524 (The Pile)

Max Activating Token Index: 218

Text #16

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.5587. Min Act: -0.0000

Data Index: 955409 (The Pile)

Max Activating Token Index: 951

Text #17

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.5738. Min Act: -0.0000

Data Index: 1420090 (The Pile)

Max Activating Token Index: 320

Text #18

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.5689. Min Act: -0.0000

Data Index: 1849342 (The Pile)

Max Activating Token Index: 348

Text #19

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.5665. Min Act: -0.0000

Data Index: 1446334 (The Pile)

Max Activating Token Index: 98