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

Dataset: The Pile

Neuron 2519 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: 0.3676. Min Range: -0.3676

Max Act: 0.3676. Min Act: -0.0000

Data Index: 394345 (The Pile)

Max Activating Token Index: 243

Text #1

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.3186. Min Act: -0.0000

Data Index: 415040 (The Pile)

Max Activating Token Index: 747

Text #2

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2873. Min Act: -0.0000

Data Index: 1423160 (The Pile)

Max Activating Token Index: 727

Text #3

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2746. Min Act: -0.0000

Data Index: 1540254 (The Pile)

Max Activating Token Index: 18

Text #4

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2632. Min Act: -0.0000

Data Index: 1463709 (The Pile)

Max Activating Token Index: 216

Text #5

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2578. Min Act: -0.0000

Data Index: 15607 (The Pile)

Max Activating Token Index: 468

Text #6

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2500. Min Act: -0.0000

Data Index: 440023 (The Pile)

Max Activating Token Index: 198

Text #7

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2627. Min Act: -0.0000

Data Index: 1842653 (The Pile)

Max Activating Token Index: 583

Text #8

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2572. Min Act: -0.0000

Data Index: 1743208 (The Pile)

Max Activating Token Index: 59

Text #9

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2326. Min Act: -0.0000

Data Index: 1867559 (The Pile)

Max Activating Token Index: 105

Text #10

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2495. Min Act: -0.0000

Data Index: 1651921 (The Pile)

Max Activating Token Index: 127

Text #11

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2270. Min Act: -0.0000

Data Index: 19210 (The Pile)

Max Activating Token Index: 199

Text #12

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2479. Min Act: -0.0000

Data Index: 493838 (The Pile)

Max Activating Token Index: 850

Text #13

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2318. Min Act: -0.0000

Data Index: 1590597 (The Pile)

Max Activating Token Index: 71

Text #14

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2529. Min Act: -0.0000

Data Index: 1315920 (The Pile)

Max Activating Token Index: 743

Text #15

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2344. Min Act: -0.0000

Data Index: 443396 (The Pile)

Max Activating Token Index: 51

Text #16

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2311. Min Act: -0.0000

Data Index: 1127164 (The Pile)

Max Activating Token Index: 70

Text #17

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2368. Min Act: -0.0000

Data Index: 1430536 (The Pile)

Max Activating Token Index: 196

Text #18

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2285. Min Act: -0.0000

Data Index: 495528 (The Pile)

Max Activating Token Index: 19

Text #19

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2258. Min Act: -0.0000

Data Index: 1373380 (The Pile)

Max Activating Token Index: 566