Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 766 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5262. Min Range: -1.5262

Max Act: 1.5262. Min Act: -0.0000

Data Index: 297181 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 1.5262. Min Range: -1.5262

Max Act: 1.3443. Min Act: -0.0000

Data Index: 299224 (C4 (Web Text))

Max Activating Token Index: 576

Text #2

Max Range: 1.5262. Min Range: -1.5262

Max Act: 1.2394. Min Act: -0.0000

Data Index: 7614 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 1.5262. Min Range: -1.5262

Max Act: 1.3208. Min Act: -0.0000

Data Index: 1211851 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 1.5262. Min Range: -1.5262

Max Act: 1.2998. Min Act: -0.0000

Data Index: 1299740 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 1.5262. Min Range: -1.5262

Max Act: 1.2667. Min Act: -0.0000

Data Index: 1157570 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 1.5262. Min Range: -1.5262

Max Act: 1.2784. Min Act: -0.0000

Data Index: 427879 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 1.5262. Min Range: -1.5262

Max Act: 1.2758. Min Act: -0.0000

Data Index: 360810 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 1.5262. Min Range: -1.5262

Max Act: 1.2582. Min Act: -0.0000

Data Index: 976316 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 1.5262. Min Range: -1.5262

Max Act: 1.2578. Min Act: -0.0000

Data Index: 698607 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 1.5262. Min Range: -1.5262

Max Act: 1.3239. Min Act: -0.0000

Data Index: 183247 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 1.5262. Min Range: -1.5262

Max Act: 1.1707. Min Act: -0.0000

Data Index: 225553 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 1.5262. Min Range: -1.5262

Max Act: 1.3065. Min Act: -0.0000

Data Index: 60022 (C4 (Web Text))

Max Activating Token Index: 789

Text #13

Max Range: 1.5262. Min Range: -1.5262

Max Act: 1.1386. Min Act: -0.0000

Data Index: 1187274 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 1.5262. Min Range: -1.5262

Max Act: 1.1330. Min Act: -0.0000

Data Index: 508310 (C4 (Web Text))

Max Activating Token Index: 810

Text #15

Max Range: 1.5262. Min Range: -1.5262

Max Act: 1.1193. Min Act: -0.0000

Data Index: 1217811 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 1.5262. Min Range: -1.5262

Max Act: 1.2657. Min Act: -0.0000

Data Index: 1047405 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 1.5262. Min Range: -1.5262

Max Act: 1.1832. Min Act: -0.0000

Data Index: 754119 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 1.5262. Min Range: -1.5262

Max Act: 1.1759. Min Act: -0.0000

Data Index: 524370 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 1.5262. Min Range: -1.5262

Max Act: 1.1841. Min Act: -0.0000

Data Index: 1300209 (C4 (Web Text))

Max Activating Token Index: 686