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

Dataset: The Pile

Neuron 4404 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.2435. Min Act: -0.0000

Data Index: 267424 (The Pile)

Max Activating Token Index: 148

Text #1

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.2175. Min Act: -0.0000

Data Index: 1220175 (The Pile)

Max Activating Token Index: 569

Text #2

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1909. Min Act: -0.0000

Data Index: 432483 (The Pile)

Max Activating Token Index: 189

Text #3

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1498. Min Act: -0.0000

Data Index: 1270102 (The Pile)

Max Activating Token Index: 318

Text #4

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1689. Min Act: -0.0000

Data Index: 1070578 (The Pile)

Max Activating Token Index: 358

Text #5

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1622. Min Act: -0.0000

Data Index: 1355144 (The Pile)

Max Activating Token Index: 304

Text #6

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1590. Min Act: -0.0000

Data Index: 873663 (The Pile)

Max Activating Token Index: 75

Text #7

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1796. Min Act: -0.0000

Data Index: 338511 (The Pile)

Max Activating Token Index: 654

Text #8

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1463. Min Act: -0.0000

Data Index: 205017 (The Pile)

Max Activating Token Index: 318

Text #9

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1414. Min Act: -0.0000

Data Index: 1119522 (The Pile)

Max Activating Token Index: 62

Text #10

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1309. Min Act: -0.0000

Data Index: 407215 (The Pile)

Max Activating Token Index: 1012

Text #11

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1574. Min Act: -0.0000

Data Index: 623416 (The Pile)

Max Activating Token Index: 144

Text #12

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1428. Min Act: -0.0000

Data Index: 522725 (The Pile)

Max Activating Token Index: 117

Text #13

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1590. Min Act: -0.0000

Data Index: 771765 (The Pile)

Max Activating Token Index: 76

Text #14

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1527. Min Act: -0.0000

Data Index: 523688 (The Pile)

Max Activating Token Index: 487

Text #15

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1498. Min Act: -0.0000

Data Index: 1446548 (The Pile)

Max Activating Token Index: 259

Text #16

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1489. Min Act: -0.0000

Data Index: 470134 (The Pile)

Max Activating Token Index: 546

Text #17

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1339. Min Act: -0.0000

Data Index: 162532 (The Pile)

Max Activating Token Index: 110

Text #18

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1542. Min Act: -0.0000

Data Index: 1248658 (The Pile)

Max Activating Token Index: 264

Text #19

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1446. Min Act: -0.0000

Data Index: 190226 (The Pile)

Max Activating Token Index: 142