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

Dataset: The Pile

Neuron 1710 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.3818. Min Act: -0.0000

Data Index: 1999852 (The Pile)

Max Activating Token Index: 86

Text #1

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.4216. Min Act: -0.0000

Data Index: 917918 (The Pile)

Max Activating Token Index: 110

Text #2

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.4262. Min Act: -0.0000

Data Index: 768283 (The Pile)

Max Activating Token Index: 629

Text #3

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.4425. Min Act: -0.0000

Data Index: 1243147 (The Pile)

Max Activating Token Index: 950

Text #4

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.3886. Min Act: -0.0000

Data Index: 1154706 (The Pile)

Max Activating Token Index: 797

Text #5

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.3459. Min Act: -0.0000

Data Index: 1285272 (The Pile)

Max Activating Token Index: 861

Text #6

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.3218. Min Act: -0.0000

Data Index: 115379 (The Pile)

Max Activating Token Index: 686

Text #7

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.3139. Min Act: -0.0000

Data Index: 90731 (The Pile)

Max Activating Token Index: 423

Text #8

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.3277. Min Act: -0.0000

Data Index: 1306985 (The Pile)

Max Activating Token Index: 746

Text #9

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.3009. Min Act: -0.0000

Data Index: 1746848 (The Pile)

Max Activating Token Index: 398

Text #10

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.3488. Min Act: -0.0000

Data Index: 1899180 (The Pile)

Max Activating Token Index: 219

Text #11

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.2688. Min Act: -0.0000

Data Index: 1608224 (The Pile)

Max Activating Token Index: 978

Text #12

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.2936. Min Act: -0.0000

Data Index: 1371754 (The Pile)

Max Activating Token Index: 1018

Text #13

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.2270. Min Act: -0.0000

Data Index: 1982147 (The Pile)

Max Activating Token Index: 370

Text #14

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.2668. Min Act: -0.0000

Data Index: 1143399 (The Pile)

Max Activating Token Index: 176

Text #15

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.2411. Min Act: -0.0000

Data Index: 1516510 (The Pile)

Max Activating Token Index: 474

Text #16

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.2555. Min Act: -0.0000

Data Index: 684920 (The Pile)

Max Activating Token Index: 97

Text #17

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.2380. Min Act: -0.0000

Data Index: 96039 (The Pile)

Max Activating Token Index: 240

Text #18

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.2606. Min Act: -0.0000

Data Index: 105798 (The Pile)

Max Activating Token Index: 276

Text #19

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.2323. Min Act: -0.0000

Data Index: 562380 (The Pile)

Max Activating Token Index: 394