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

Dataset: The Pile

Neuron 2578 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8244. Min Range: -3.8244

Max Act: 3.8244. Min Act: -0.0000

Data Index: 183884 (The Pile)

Max Activating Token Index: 576

Text #1

Max Range: 3.8244. Min Range: -3.8244

Max Act: 3.6667. Min Act: -0.0000

Data Index: 732320 (The Pile)

Max Activating Token Index: 30

Text #2

Max Range: 3.8244. Min Range: -3.8244

Max Act: 3.6887. Min Act: -0.0000

Data Index: 1407911 (The Pile)

Max Activating Token Index: 190

Text #3

Max Range: 3.8244. Min Range: -3.8244

Max Act: 3.5947. Min Act: -0.0000

Data Index: 551666 (The Pile)

Max Activating Token Index: 6

Text #4

Max Range: 3.8244. Min Range: -3.8244

Max Act: 3.5857. Min Act: -0.0000

Data Index: 560954 (The Pile)

Max Activating Token Index: 570

Text #5

Max Range: 3.8244. Min Range: -3.8244

Max Act: 3.5170. Min Act: -0.0000

Data Index: 1930543 (The Pile)

Max Activating Token Index: 73

Text #6

Max Range: 3.8244. Min Range: -3.8244

Max Act: 3.4764. Min Act: -0.0000

Data Index: 1645569 (The Pile)

Max Activating Token Index: 195

Text #7

Max Range: 3.8244. Min Range: -3.8244

Max Act: 3.2836. Min Act: -0.0000

Data Index: 1397668 (The Pile)

Max Activating Token Index: 632

Text #8

Max Range: 3.8244. Min Range: -3.8244

Max Act: 3.2932. Min Act: -0.0000

Data Index: 1563262 (The Pile)

Max Activating Token Index: 293

Text #9

Max Range: 3.8244. Min Range: -3.8244

Max Act: 3.1421. Min Act: -0.0000

Data Index: 356886 (The Pile)

Max Activating Token Index: 42

Text #10

Max Range: 3.8244. Min Range: -3.8244

Max Act: 3.0483. Min Act: -0.0000

Data Index: 1755842 (The Pile)

Max Activating Token Index: 625

Text #11

Max Range: 3.8244. Min Range: -3.8244

Max Act: 3.1117. Min Act: -0.0000

Data Index: 670641 (The Pile)

Max Activating Token Index: 851

Text #12

Max Range: 3.8244. Min Range: -3.8244

Max Act: 2.9272. Min Act: -0.0000

Data Index: 1129310 (The Pile)

Max Activating Token Index: 255

Text #13

Max Range: 3.8244. Min Range: -3.8244

Max Act: 2.9426. Min Act: -0.0000

Data Index: 1172294 (The Pile)

Max Activating Token Index: 746

Text #14

Max Range: 3.8244. Min Range: -3.8244

Max Act: 2.9398. Min Act: -0.0000

Data Index: 1984873 (The Pile)

Max Activating Token Index: 527

Text #15

Max Range: 3.8244. Min Range: -3.8244

Max Act: 3.0258. Min Act: -0.0000

Data Index: 272987 (The Pile)

Max Activating Token Index: 624

Text #16

Max Range: 3.8244. Min Range: -3.8244

Max Act: 3.0339. Min Act: -0.0000

Data Index: 322415 (The Pile)

Max Activating Token Index: 55

Text #17

Max Range: 3.8244. Min Range: -3.8244

Max Act: 2.8912. Min Act: -0.0000

Data Index: 249604 (The Pile)

Max Activating Token Index: 473

Text #18

Max Range: 3.8244. Min Range: -3.8244

Max Act: 3.1750. Min Act: -0.0000

Data Index: 1121075 (The Pile)

Max Activating Token Index: 353

Text #19

Max Range: 3.8244. Min Range: -3.8244

Max Act: 2.8274. Min Act: -0.0000

Data Index: 565252 (The Pile)

Max Activating Token Index: 777