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

Dataset: The Pile

Neuron 886 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1577. Min Range: -1.1577

Max Act: 1.1546. Min Act: -0.0000

Data Index: 596413 (The Pile)

Max Activating Token Index: 201

Text #1

Max Range: 1.1577. Min Range: -1.1577

Max Act: 1.0584. Min Act: -0.0000

Data Index: 21308 (The Pile)

Max Activating Token Index: 162

Text #2

Max Range: 1.1577. Min Range: -1.1577

Max Act: 1.1577. Min Act: -0.0000

Data Index: 1086820 (The Pile)

Max Activating Token Index: 656

Text #3

Max Range: 1.1577. Min Range: -1.1577

Max Act: 1.0191. Min Act: -0.0000

Data Index: 52539 (The Pile)

Max Activating Token Index: 863

Text #4

Max Range: 1.1577. Min Range: -1.1577

Max Act: 1.0018. Min Act: -0.0000

Data Index: 982600 (The Pile)

Max Activating Token Index: 169

Text #5

Max Range: 1.1577. Min Range: -1.1577

Max Act: 0.9466. Min Act: -0.0000

Data Index: 1218912 (The Pile)

Max Activating Token Index: 544

Text #6

Max Range: 1.1577. Min Range: -1.1577

Max Act: 1.0318. Min Act: -0.0000

Data Index: 1625821 (The Pile)

Max Activating Token Index: 739

Text #7

Max Range: 1.1577. Min Range: -1.1577

Max Act: 0.8052. Min Act: -0.0000

Data Index: 1391283 (The Pile)

Max Activating Token Index: 886

Text #8

Max Range: 1.1577. Min Range: -1.1577

Max Act: 0.8614. Min Act: -0.0000

Data Index: 1888634 (The Pile)

Max Activating Token Index: 252

Text #9

Max Range: 1.1577. Min Range: -1.1577

Max Act: 0.8303. Min Act: -0.0000

Data Index: 1643568 (The Pile)

Max Activating Token Index: 465

Text #10

Max Range: 1.1577. Min Range: -1.1577

Max Act: 0.8712. Min Act: -0.0000

Data Index: 1316257 (The Pile)

Max Activating Token Index: 440

Text #11

Max Range: 1.1577. Min Range: -1.1577

Max Act: 0.8329. Min Act: -0.0000

Data Index: 316293 (The Pile)

Max Activating Token Index: 609

Text #12

Max Range: 1.1577. Min Range: -1.1577

Max Act: 0.8275. Min Act: -0.0000

Data Index: 1456297 (The Pile)

Max Activating Token Index: 835

Text #13

Max Range: 1.1577. Min Range: -1.1577

Max Act: 0.7369. Min Act: -0.0000

Data Index: 457228 (The Pile)

Max Activating Token Index: 1017

Text #14

Max Range: 1.1577. Min Range: -1.1577

Max Act: 0.7762. Min Act: -0.0001

Data Index: 704225 (The Pile)

Max Activating Token Index: 191

Text #15

Max Range: 1.1577. Min Range: -1.1577

Max Act: 0.7430. Min Act: -0.0000

Data Index: 606228 (The Pile)

Max Activating Token Index: 812

Text #16

Max Range: 1.1577. Min Range: -1.1577

Max Act: 0.7831. Min Act: -0.0000

Data Index: 1979208 (The Pile)

Max Activating Token Index: 437

Text #17

Max Range: 1.1577. Min Range: -1.1577

Max Act: 0.6776. Min Act: -0.0000

Data Index: 1638627 (The Pile)

Max Activating Token Index: 879

Text #18

Max Range: 1.1577. Min Range: -1.1577

Max Act: 0.7986. Min Act: -0.0000

Data Index: 293362 (The Pile)

Max Activating Token Index: 502

Text #19

Max Range: 1.1577. Min Range: -1.1577

Max Act: 0.7062. Min Act: -0.0000

Data Index: 386721 (The Pile)

Max Activating Token Index: 460