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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 793 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2638. Min Act: -0.0000

Data Index: 669865 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2786. Min Act: -0.0000

Data Index: 110006 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2507. Min Act: -0.0000

Data Index: 785468 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2548. Min Act: -0.0000

Data Index: 463247 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2390. Min Act: -0.0000

Data Index: 605982 (C4 (Web Text))

Max Activating Token Index: 408

Text #5

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2544. Min Act: -0.0000

Data Index: 392098 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2393. Min Act: -0.0000

Data Index: 641399 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2489. Min Act: -0.0000

Data Index: 657223 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2358. Min Act: -0.0000

Data Index: 865079 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2449. Min Act: -0.0000

Data Index: 535111 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2343. Min Act: -0.0000

Data Index: 835000 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2244. Min Act: -0.0000

Data Index: 1313457 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2317. Min Act: -0.0000

Data Index: 231803 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2162. Min Act: -0.0000

Data Index: 518021 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2296. Min Act: -0.0000

Data Index: 175473 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2265. Min Act: -0.0000

Data Index: 117665 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2266. Min Act: -0.0000

Data Index: 1213822 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2408. Min Act: -0.0000

Data Index: 928762 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2175. Min Act: -0.0000

Data Index: 1172641 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2169. Min Act: -0.0000

Data Index: 855948 (C4 (Web Text))

Max Activating Token Index: 617