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

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

Neuron 4605 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.2512. Min Act: -0.0000

Data Index: 1312402 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.2509. Min Act: -0.0000

Data Index: 1064499 (C4 (Web Text))

Max Activating Token Index: 877

Text #2

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.2437. Min Act: -0.0000

Data Index: 582702 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.2323. Min Act: -0.0000

Data Index: 918415 (C4 (Web Text))

Max Activating Token Index: 475

Text #4

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.2314. Min Act: -0.0000

Data Index: 1084531 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.2409. Min Act: -0.0000

Data Index: 152016 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.2331. Min Act: -0.0000

Data Index: 1124455 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.2232. Min Act: -0.0000

Data Index: 471367 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.2312. Min Act: -0.0000

Data Index: 1274095 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.2227. Min Act: -0.0000

Data Index: 64967 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.2277. Min Act: -0.0000

Data Index: 301040 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.2320. Min Act: -0.0000

Data Index: 641604 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.2233. Min Act: -0.0000

Data Index: 293153 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.2451. Min Act: -0.0000

Data Index: 1077326 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.2337. Min Act: -0.0000

Data Index: 785926 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.2202. Min Act: -0.0000

Data Index: 649195 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.2327. Min Act: -0.0000

Data Index: 1209204 (C4 (Web Text))

Max Activating Token Index: 830

Text #17

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.2159. Min Act: -0.0000

Data Index: 547820 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.2092. Min Act: -0.0000

Data Index: 1358543 (C4 (Web Text))

Max Activating Token Index: 922

Text #19

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.2135. Min Act: -0.0000

Data Index: 295029 (C4 (Web Text))

Max Activating Token Index: 501