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

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

Neuron 4014 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8064. Min Range: -1.8064

Max Act: 1.8064. Min Act: -0.0000

Data Index: 700119 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 1.8064. Min Range: -1.8064

Max Act: 1.4803. Min Act: -0.0000

Data Index: 240399 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 1.8064. Min Range: -1.8064

Max Act: 1.5240. Min Act: -0.0000

Data Index: 299212 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 1.8064. Min Range: -1.8064

Max Act: 1.5780. Min Act: -0.0000

Data Index: 1272974 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 1.8064. Min Range: -1.8064

Max Act: 1.4008. Min Act: -0.0000

Data Index: 839391 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 1.8064. Min Range: -1.8064

Max Act: 1.2526. Min Act: -0.0000

Data Index: 295481 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 1.8064. Min Range: -1.8064

Max Act: 1.2466. Min Act: -0.0000

Data Index: 1152015 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 1.8064. Min Range: -1.8064

Max Act: 1.2917. Min Act: -0.0000

Data Index: 32249 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 1.8064. Min Range: -1.8064

Max Act: 1.2102. Min Act: -0.0000

Data Index: 341298 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 1.8064. Min Range: -1.8064

Max Act: 1.2785. Min Act: -0.0000

Data Index: 423167 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 1.8064. Min Range: -1.8064

Max Act: 1.1761. Min Act: -0.0000

Data Index: 226817 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 1.8064. Min Range: -1.8064

Max Act: 1.1354. Min Act: -0.0000

Data Index: 451527 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 1.8064. Min Range: -1.8064

Max Act: 1.1893. Min Act: -0.0000

Data Index: 286886 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 1.8064. Min Range: -1.8064

Max Act: 1.1583. Min Act: -0.0000

Data Index: 1225673 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 1.8064. Min Range: -1.8064

Max Act: 1.1518. Min Act: -0.0000

Data Index: 360842 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 1.8064. Min Range: -1.8064

Max Act: 1.1382. Min Act: -0.0000

Data Index: 244407 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 1.8064. Min Range: -1.8064

Max Act: 1.0716. Min Act: -0.0000

Data Index: 645061 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 1.8064. Min Range: -1.8064

Max Act: 1.1980. Min Act: -0.0000

Data Index: 761018 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 1.8064. Min Range: -1.8064

Max Act: 1.0563. Min Act: -0.0000

Data Index: 379478 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 1.8064. Min Range: -1.8064

Max Act: 1.1137. Min Act: -0.0000

Data Index: 1075418 (C4 (Web Text))

Max Activating Token Index: 599