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

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

Neuron 4981 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.7063. Min Act: 0.0000

Data Index: 93891 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.7289. Min Act: -0.0000

Data Index: 1301136 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.6067. Min Act: -0.0000

Data Index: 792122 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.6441. Min Act: -0.0000

Data Index: 909354 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.6212. Min Act: 0.0000

Data Index: 794171 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5722. Min Act: -0.0000

Data Index: 489617 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5805. Min Act: -0.0000

Data Index: 1547138 (Python Code)

Max Activating Token Index: 402

Text #7

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5985. Min Act: -0.0000

Data Index: 415917 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5805. Min Act: -0.0000

Data Index: 135587 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5592. Min Act: -0.0000

Data Index: 469679 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5103. Min Act: -0.0000

Data Index: 740923 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.4532. Min Act: -0.0000

Data Index: 491617 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.4503. Min Act: -0.0000

Data Index: 778278 (C4 (Web Text))

Max Activating Token Index: 881

Text #13

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.4923. Min Act: -0.0000

Data Index: 1328863 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.4356. Min Act: -0.0000

Data Index: 967784 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.4581. Min Act: -0.0000

Data Index: 378395 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.4721. Min Act: -0.0000

Data Index: 500673 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.4668. Min Act: 0.0000

Data Index: 311614 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.4641. Min Act: 0.0000

Data Index: 792304 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5042. Min Act: -0.0000

Data Index: 253828 (C4 (Web Text))

Max Activating Token Index: 854