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

Dataset: The Pile

Neuron 189 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3433. Min Range: -1.3433

Max Act: 1.3433. Min Act: -0.0000

Data Index: 1261798 (The Pile)

Max Activating Token Index: 429

Text #1

Max Range: 1.3433. Min Range: -1.3433

Max Act: 1.0216. Min Act: -0.0000

Data Index: 179804 (The Pile)

Max Activating Token Index: 680

Text #2

Max Range: 1.3433. Min Range: -1.3433

Max Act: 1.0708. Min Act: -0.0000

Data Index: 81348 (The Pile)

Max Activating Token Index: 982

Text #3

Max Range: 1.3433. Min Range: -1.3433

Max Act: 0.8682. Min Act: -0.0000

Data Index: 1100990 (The Pile)

Max Activating Token Index: 592

Text #4

Max Range: 1.3433. Min Range: -1.3433

Max Act: 0.8909. Min Act: -0.0000

Data Index: 1197342 (The Pile)

Max Activating Token Index: 352

Text #5

Max Range: 1.3433. Min Range: -1.3433

Max Act: 0.7518. Min Act: -0.0000

Data Index: 91466 (The Pile)

Max Activating Token Index: 900

Text #6

Max Range: 1.3433. Min Range: -1.3433

Max Act: 0.8273. Min Act: -0.0000

Data Index: 1020100 (The Pile)

Max Activating Token Index: 527

Text #7

Max Range: 1.3433. Min Range: -1.3433

Max Act: 0.7741. Min Act: -0.0000

Data Index: 633052 (The Pile)

Max Activating Token Index: 281

Text #8

Max Range: 1.3433. Min Range: -1.3433

Max Act: 0.6496. Min Act: -0.0000

Data Index: 1692339 (The Pile)

Max Activating Token Index: 891

Text #9

Max Range: 1.3433. Min Range: -1.3433

Max Act: 0.7651. Min Act: -0.0000

Data Index: 948162 (The Pile)

Max Activating Token Index: 536

Text #10

Max Range: 1.3433. Min Range: -1.3433

Max Act: 0.7304. Min Act: -0.0000

Data Index: 1771210 (The Pile)

Max Activating Token Index: 618

Text #11

Max Range: 1.3433. Min Range: -1.3433

Max Act: 0.6900. Min Act: -0.0000

Data Index: 647402 (The Pile)

Max Activating Token Index: 130

Text #12

Max Range: 1.3433. Min Range: -1.3433

Max Act: 0.6860. Min Act: -0.0000

Data Index: 101605 (The Pile)

Max Activating Token Index: 123

Text #13

Max Range: 1.3433. Min Range: -1.3433

Max Act: 0.6283. Min Act: -0.0000

Data Index: 1451902 (The Pile)

Max Activating Token Index: 598

Text #14

Max Range: 1.3433. Min Range: -1.3433

Max Act: 0.6185. Min Act: -0.0000

Data Index: 1506872 (The Pile)

Max Activating Token Index: 897

Text #15

Max Range: 1.3433. Min Range: -1.3433

Max Act: 0.6510. Min Act: -0.0000

Data Index: 263615 (The Pile)

Max Activating Token Index: 1011

Text #16

Max Range: 1.3433. Min Range: -1.3433

Max Act: 0.5955. Min Act: -0.0000

Data Index: 998697 (The Pile)

Max Activating Token Index: 812

Text #17

Max Range: 1.3433. Min Range: -1.3433

Max Act: 0.5932. Min Act: -0.0000

Data Index: 1274971 (The Pile)

Max Activating Token Index: 982

Text #18

Max Range: 1.3433. Min Range: -1.3433

Max Act: 0.6532. Min Act: -0.0000

Data Index: 1027578 (The Pile)

Max Activating Token Index: 424

Text #19

Max Range: 1.3433. Min Range: -1.3433

Max Act: 0.6320. Min Act: 0.0000

Data Index: 232336 (The Pile)

Max Activating Token Index: 843