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

Dataset: The Pile

Neuron 4770 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3514. Min Range: -1.3514

Max Act: 1.2258. Min Act: -0.0000

Data Index: 1016580 (The Pile)

Max Activating Token Index: 101

Text #1

Max Range: 1.3514. Min Range: -1.3514

Max Act: 1.2252. Min Act: -0.0000

Data Index: 365380 (The Pile)

Max Activating Token Index: 924

Text #2

Max Range: 1.3514. Min Range: -1.3514

Max Act: 1.2678. Min Act: -0.0000

Data Index: 1733292 (The Pile)

Max Activating Token Index: 911

Text #3

Max Range: 1.3514. Min Range: -1.3514

Max Act: 1.2653. Min Act: -0.0000

Data Index: 1405000 (The Pile)

Max Activating Token Index: 307

Text #4

Max Range: 1.3514. Min Range: -1.3514

Max Act: 1.1529. Min Act: -0.0000

Data Index: 80389 (The Pile)

Max Activating Token Index: 253

Text #5

Max Range: 1.3514. Min Range: -1.3514

Max Act: 1.3514. Min Act: -0.0000

Data Index: 1460815 (The Pile)

Max Activating Token Index: 1013

Text #6

Max Range: 1.3514. Min Range: -1.3514

Max Act: 1.1775. Min Act: -0.0000

Data Index: 1128570 (The Pile)

Max Activating Token Index: 241

Text #7

Max Range: 1.3514. Min Range: -1.3514

Max Act: 1.1376. Min Act: -0.0000

Data Index: 1401532 (The Pile)

Max Activating Token Index: 174

Text #8

Max Range: 1.3514. Min Range: -1.3514

Max Act: 1.1165. Min Act: -0.0000

Data Index: 538073 (The Pile)

Max Activating Token Index: 698

Text #9

Max Range: 1.3514. Min Range: -1.3514

Max Act: 1.1732. Min Act: -0.0000

Data Index: 1186771 (The Pile)

Max Activating Token Index: 290

Text #10

Max Range: 1.3514. Min Range: -1.3514

Max Act: 1.0728. Min Act: -0.0000

Data Index: 966293 (The Pile)

Max Activating Token Index: 175

Text #11

Max Range: 1.3514. Min Range: -1.3514

Max Act: 1.0778. Min Act: -0.0000

Data Index: 1980088 (The Pile)

Max Activating Token Index: 547

Text #12

Max Range: 1.3514. Min Range: -1.3514

Max Act: 1.0790. Min Act: -0.0000

Data Index: 1459851 (The Pile)

Max Activating Token Index: 361

Text #13

Max Range: 1.3514. Min Range: -1.3514

Max Act: 1.0659. Min Act: -0.0000

Data Index: 630912 (The Pile)

Max Activating Token Index: 424

Text #14

Max Range: 1.3514. Min Range: -1.3514

Max Act: 0.8897. Min Act: -0.0000

Data Index: 234911 (The Pile)

Max Activating Token Index: 678

Text #15

Max Range: 1.3514. Min Range: -1.3514

Max Act: 0.9930. Min Act: -0.0000

Data Index: 1732928 (The Pile)

Max Activating Token Index: 757

Text #16

Max Range: 1.3514. Min Range: -1.3514

Max Act: 1.0476. Min Act: -0.0000

Data Index: 805316 (The Pile)

Max Activating Token Index: 287

Text #17

Max Range: 1.3514. Min Range: -1.3514

Max Act: 1.0998. Min Act: -0.0000

Data Index: 574582 (The Pile)

Max Activating Token Index: 819

Text #18

Max Range: 1.3514. Min Range: -1.3514

Max Act: 1.0221. Min Act: -0.0000

Data Index: 1989160 (The Pile)

Max Activating Token Index: 847

Text #19

Max Range: 1.3514. Min Range: -1.3514

Max Act: 1.0275. Min Act: -0.0000

Data Index: 1354330 (The Pile)

Max Activating Token Index: 312