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

Dataset: The Pile

Neuron 3163 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.6475. Min Range: -1.6475

Max Act: 1.6475. Min Act: -0.0000

Data Index: 1407514 (The Pile)

Max Activating Token Index: 345

Text #1

Max Range: 1.6475. Min Range: -1.6475

Max Act: 1.4284. Min Act: -0.0000

Data Index: 1570633 (The Pile)

Max Activating Token Index: 395

Text #2

Max Range: 1.6475. Min Range: -1.6475

Max Act: 1.4545. Min Act: -0.0000

Data Index: 1874605 (The Pile)

Max Activating Token Index: 458

Text #3

Max Range: 1.6475. Min Range: -1.6475

Max Act: 1.6030. Min Act: -0.0000

Data Index: 1546636 (The Pile)

Max Activating Token Index: 164

Text #4

Max Range: 1.6475. Min Range: -1.6475

Max Act: 1.5133. Min Act: -0.0000

Data Index: 1378145 (The Pile)

Max Activating Token Index: 536

Text #5

Max Range: 1.6475. Min Range: -1.6475

Max Act: 1.3835. Min Act: -0.0000

Data Index: 1633816 (The Pile)

Max Activating Token Index: 791

Text #6

Max Range: 1.6475. Min Range: -1.6475

Max Act: 1.3352. Min Act: -0.0000

Data Index: 615433 (The Pile)

Max Activating Token Index: 205

Text #7

Max Range: 1.6475. Min Range: -1.6475

Max Act: 1.2818. Min Act: -0.0000

Data Index: 52523 (The Pile)

Max Activating Token Index: 228

Text #8

Max Range: 1.6475. Min Range: -1.6475

Max Act: 1.2151. Min Act: -0.0000

Data Index: 1601845 (The Pile)

Max Activating Token Index: 28

Text #9

Max Range: 1.6475. Min Range: -1.6475

Max Act: 1.2898. Min Act: -0.0000

Data Index: 1390496 (The Pile)

Max Activating Token Index: 557

Text #10

Max Range: 1.6475. Min Range: -1.6475

Max Act: 1.2446. Min Act: -0.0000

Data Index: 1505417 (The Pile)

Max Activating Token Index: 71

Text #11

Max Range: 1.6475. Min Range: -1.6475

Max Act: 1.1733. Min Act: -0.0000

Data Index: 1049402 (The Pile)

Max Activating Token Index: 427

Text #12

Max Range: 1.6475. Min Range: -1.6475

Max Act: 1.0674. Min Act: -0.0000

Data Index: 1346190 (The Pile)

Max Activating Token Index: 254

Text #13

Max Range: 1.6475. Min Range: -1.6475

Max Act: 1.1636. Min Act: -0.0000

Data Index: 62957 (The Pile)

Max Activating Token Index: 907

Text #14

Max Range: 1.6475. Min Range: -1.6475

Max Act: 1.0675. Min Act: -0.0000

Data Index: 1306683 (The Pile)

Max Activating Token Index: 257

Text #15

Max Range: 1.6475. Min Range: -1.6475

Max Act: 1.0897. Min Act: -0.0000

Data Index: 395148 (The Pile)

Max Activating Token Index: 86

Text #16

Max Range: 1.6475. Min Range: -1.6475

Max Act: 1.1075. Min Act: -0.0000

Data Index: 881313 (The Pile)

Max Activating Token Index: 705

Text #17

Max Range: 1.6475. Min Range: -1.6475

Max Act: 0.9525. Min Act: -0.0000

Data Index: 1594083 (The Pile)

Max Activating Token Index: 639

Text #18

Max Range: 1.6475. Min Range: -1.6475

Max Act: 0.9565. Min Act: -0.0000

Data Index: 1538214 (The Pile)

Max Activating Token Index: 854

Text #19

Max Range: 1.6475. Min Range: -1.6475

Max Act: 1.0607. Min Act: -0.0000

Data Index: 1591465 (The Pile)

Max Activating Token Index: 703