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

Dataset: The Pile

Neuron 2514 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: 0.3372. Min Range: -0.3372

Max Act: 0.3372. Min Act: -0.0000

Data Index: 1786887 (The Pile)

Max Activating Token Index: 254

Text #1

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.3301. Min Act: -0.0000

Data Index: 862648 (The Pile)

Max Activating Token Index: 708

Text #2

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.3048. Min Act: -0.0000

Data Index: 818624 (The Pile)

Max Activating Token Index: 25

Text #3

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2761. Min Act: -0.0000

Data Index: 1313908 (The Pile)

Max Activating Token Index: 602

Text #4

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2906. Min Act: -0.0000

Data Index: 1177703 (The Pile)

Max Activating Token Index: 375

Text #5

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2612. Min Act: -0.0000

Data Index: 1935809 (The Pile)

Max Activating Token Index: 103

Text #6

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2604. Min Act: -0.0000

Data Index: 999463 (The Pile)

Max Activating Token Index: 479

Text #7

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2700. Min Act: -0.0000

Data Index: 228757 (The Pile)

Max Activating Token Index: 135

Text #8

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2761. Min Act: -0.0000

Data Index: 604601 (The Pile)

Max Activating Token Index: 451

Text #9

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2728. Min Act: -0.0000

Data Index: 1428727 (The Pile)

Max Activating Token Index: 542

Text #10

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2616. Min Act: -0.0000

Data Index: 1583713 (The Pile)

Max Activating Token Index: 93

Text #11

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2583. Min Act: -0.0000

Data Index: 1929675 (The Pile)

Max Activating Token Index: 94

Text #12

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2493. Min Act: -0.0000

Data Index: 1626178 (The Pile)

Max Activating Token Index: 856

Text #13

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2594. Min Act: -0.0000

Data Index: 1976 (The Pile)

Max Activating Token Index: 466

Text #14

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2657. Min Act: -0.0000

Data Index: 64819 (The Pile)

Max Activating Token Index: 469

Text #15

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2317. Min Act: -0.0000

Data Index: 1863370 (The Pile)

Max Activating Token Index: 74

Text #16

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2426. Min Act: -0.0000

Data Index: 363478 (The Pile)

Max Activating Token Index: 815

Text #17

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2439. Min Act: -0.0000

Data Index: 1243180 (The Pile)

Max Activating Token Index: 460

Text #18

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2378. Min Act: -0.0000

Data Index: 809416 (The Pile)

Max Activating Token Index: 117

Text #19

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2535. Min Act: -0.0000

Data Index: 62461 (The Pile)

Max Activating Token Index: 216