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

Dataset: The Pile

Neuron 2458 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: 1.8864. Min Range: -1.8864

Max Act: 1.8864. Min Act: -0.0000

Data Index: 1865334 (The Pile)

Max Activating Token Index: 733

Text #1

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.5827. Min Act: -0.0000

Data Index: 356360 (The Pile)

Max Activating Token Index: 363

Text #2

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.4489. Min Act: -0.0000

Data Index: 378558 (The Pile)

Max Activating Token Index: 660

Text #3

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.4578. Min Act: -0.0000

Data Index: 1539399 (The Pile)

Max Activating Token Index: 550

Text #4

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.4411. Min Act: -0.0000

Data Index: 556323 (The Pile)

Max Activating Token Index: 985

Text #5

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.5275. Min Act: -0.0000

Data Index: 884059 (The Pile)

Max Activating Token Index: 966

Text #6

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.3555. Min Act: -0.0000

Data Index: 665548 (The Pile)

Max Activating Token Index: 546

Text #7

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.4517. Min Act: -0.0000

Data Index: 506278 (The Pile)

Max Activating Token Index: 712

Text #8

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.2453. Min Act: -0.0000

Data Index: 1763064 (The Pile)

Max Activating Token Index: 685

Text #9

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.3219. Min Act: -0.0000

Data Index: 112327 (The Pile)

Max Activating Token Index: 598

Text #10

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.3586. Min Act: -0.0000

Data Index: 950158 (The Pile)

Max Activating Token Index: 829

Text #11

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.3567. Min Act: -0.0000

Data Index: 1079011 (The Pile)

Max Activating Token Index: 905

Text #12

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.1968. Min Act: -0.0000

Data Index: 491832 (The Pile)

Max Activating Token Index: 628

Text #13

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.3480. Min Act: -0.0000

Data Index: 1851960 (The Pile)

Max Activating Token Index: 157

Text #14

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.2313. Min Act: -0.0000

Data Index: 1070433 (The Pile)

Max Activating Token Index: 395

Text #15

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.2660. Min Act: -0.0000

Data Index: 1361429 (The Pile)

Max Activating Token Index: 11

Text #16

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.2336. Min Act: -0.0000

Data Index: 1354938 (The Pile)

Max Activating Token Index: 780

Text #17

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.1943. Min Act: -0.0000

Data Index: 698961 (The Pile)

Max Activating Token Index: 974

Text #18

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.2884. Min Act: -0.0000

Data Index: 112127 (The Pile)

Max Activating Token Index: 681

Text #19

Max Range: 1.8864. Min Range: -1.8864

Max Act: 1.1223. Min Act: -0.0000

Data Index: 898876 (The Pile)

Max Activating Token Index: 881