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

Dataset: The Pile

Neuron 1265 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.4338. Min Act: -0.0000

Data Index: 635910 (The Pile)

Max Activating Token Index: 208

Text #1

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3826. Min Act: -0.0000

Data Index: 1793459 (The Pile)

Max Activating Token Index: 947

Text #2

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.4188. Min Act: -0.0000

Data Index: 6322 (The Pile)

Max Activating Token Index: 206

Text #3

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.4165. Min Act: -0.0000

Data Index: 941826 (The Pile)

Max Activating Token Index: 630

Text #4

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3422. Min Act: -0.0000

Data Index: 833879 (The Pile)

Max Activating Token Index: 457

Text #5

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3505. Min Act: -0.0000

Data Index: 1594893 (The Pile)

Max Activating Token Index: 458

Text #6

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3412. Min Act: -0.0000

Data Index: 1515644 (The Pile)

Max Activating Token Index: 403

Text #7

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3457. Min Act: -0.0000

Data Index: 1841850 (The Pile)

Max Activating Token Index: 417

Text #8

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3363. Min Act: -0.0000

Data Index: 1984505 (The Pile)

Max Activating Token Index: 551

Text #9

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3356. Min Act: -0.0000

Data Index: 57199 (The Pile)

Max Activating Token Index: 409

Text #10

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3193. Min Act: -0.0000

Data Index: 878082 (The Pile)

Max Activating Token Index: 300

Text #11

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3364. Min Act: -0.0000

Data Index: 1246482 (The Pile)

Max Activating Token Index: 391

Text #12

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3359. Min Act: -0.0000

Data Index: 1694872 (The Pile)

Max Activating Token Index: 644

Text #13

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3286. Min Act: -0.0000

Data Index: 1520999 (The Pile)

Max Activating Token Index: 847

Text #14

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3633. Min Act: -0.0000

Data Index: 1822677 (The Pile)

Max Activating Token Index: 324

Text #15

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.2935. Min Act: -0.0000

Data Index: 622697 (The Pile)

Max Activating Token Index: 967

Text #16

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3189. Min Act: -0.0000

Data Index: 1434792 (The Pile)

Max Activating Token Index: 874

Text #17

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.2941. Min Act: -0.0000

Data Index: 557573 (The Pile)

Max Activating Token Index: 411

Text #18

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3134. Min Act: -0.0000

Data Index: 1894514 (The Pile)

Max Activating Token Index: 622

Text #19

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3296. Min Act: -0.0000

Data Index: 226729 (The Pile)

Max Activating Token Index: 328