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

Dataset: The Pile

Neuron 3013 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.3213. Min Act: -0.0000

Data Index: 1267103 (The Pile)

Max Activating Token Index: 403

Text #1

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.3272. Min Act: -0.0000

Data Index: 506310 (The Pile)

Max Activating Token Index: 570

Text #2

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.3330. Min Act: -0.0000

Data Index: 836359 (The Pile)

Max Activating Token Index: 169

Text #3

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2870. Min Act: 0.0000

Data Index: 594791 (The Pile)

Max Activating Token Index: 621

Text #4

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2963. Min Act: -0.0000

Data Index: 96824 (The Pile)

Max Activating Token Index: 238

Text #5

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2928. Min Act: -0.0000

Data Index: 670717 (The Pile)

Max Activating Token Index: 434

Text #6

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2652. Min Act: -0.0000

Data Index: 1564023 (The Pile)

Max Activating Token Index: 485

Text #7

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2752. Min Act: -0.0000

Data Index: 1915542 (The Pile)

Max Activating Token Index: 447

Text #8

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2632. Min Act: -0.0000

Data Index: 837303 (The Pile)

Max Activating Token Index: 888

Text #9

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2416. Min Act: -0.0000

Data Index: 1019902 (The Pile)

Max Activating Token Index: 982

Text #10

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2506. Min Act: -0.0000

Data Index: 1347374 (The Pile)

Max Activating Token Index: 172

Text #11

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2398. Min Act: -0.0000

Data Index: 493636 (The Pile)

Max Activating Token Index: 225

Text #12

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2300. Min Act: -0.0000

Data Index: 1556076 (The Pile)

Max Activating Token Index: 735

Text #13

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2384. Min Act: -0.0000

Data Index: 1255898 (The Pile)

Max Activating Token Index: 102

Text #14

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2239. Min Act: 0.0000

Data Index: 1859548 (The Pile)

Max Activating Token Index: 917

Text #15

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2246. Min Act: -0.0000

Data Index: 1518882 (The Pile)

Max Activating Token Index: 338

Text #16

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2271. Min Act: -0.0000

Data Index: 1828652 (The Pile)

Max Activating Token Index: 841

Text #17

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2336. Min Act: -0.0000

Data Index: 1237047 (The Pile)

Max Activating Token Index: 246

Text #18

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2242. Min Act: -0.0000

Data Index: 1348228 (The Pile)

Max Activating Token Index: 417

Text #19

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2326. Min Act: -0.0000

Data Index: 1486303 (The Pile)

Max Activating Token Index: 450