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

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

Neuron 3415 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0395. Min Range: -5.0395

Max Act: 5.0395. Min Act: -0.0001

Data Index: 191719 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 5.0395. Min Range: -5.0395

Max Act: 4.2896. Min Act: -0.0000

Data Index: 1041937 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 5.0395. Min Range: -5.0395

Max Act: 4.1832. Min Act: -0.0001

Data Index: 386761 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 5.0395. Min Range: -5.0395

Max Act: 4.3118. Min Act: -0.0000

Data Index: 975254 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 5.0395. Min Range: -5.0395

Max Act: 4.2107. Min Act: -0.0001

Data Index: 1350743 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 5.0395. Min Range: -5.0395

Max Act: 3.8316. Min Act: -0.0000

Data Index: 984918 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 5.0395. Min Range: -5.0395

Max Act: 3.6164. Min Act: -0.0001

Data Index: 865295 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 5.0395. Min Range: -5.0395

Max Act: 3.5691. Min Act: -0.0000

Data Index: 1136368 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 5.0395. Min Range: -5.0395

Max Act: 3.4445. Min Act: -0.0001

Data Index: 1147469 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 5.0395. Min Range: -5.0395

Max Act: 3.8074. Min Act: -0.0000

Data Index: 869076 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 5.0395. Min Range: -5.0395

Max Act: 3.3032. Min Act: -0.0001

Data Index: 110997 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 5.0395. Min Range: -5.0395

Max Act: 3.1782. Min Act: -0.0000

Data Index: 166579 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 5.0395. Min Range: -5.0395

Max Act: 3.3042. Min Act: -0.0001

Data Index: 1145816 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 5.0395. Min Range: -5.0395

Max Act: 2.7703. Min Act: -0.0000

Data Index: 1222200 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 5.0395. Min Range: -5.0395

Max Act: 3.2271. Min Act: -0.0001

Data Index: 93612 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 5.0395. Min Range: -5.0395

Max Act: 3.1821. Min Act: -0.0001

Data Index: 788381 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 5.0395. Min Range: -5.0395

Max Act: 2.9921. Min Act: -0.0000

Data Index: 240811 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 5.0395. Min Range: -5.0395

Max Act: 3.3065. Min Act: -0.0000

Data Index: 1318230 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 5.0395. Min Range: -5.0395

Max Act: 3.0898. Min Act: -0.0001

Data Index: 99805 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 5.0395. Min Range: -5.0395

Max Act: 3.2394. Min Act: -0.0001

Data Index: 304530 (C4 (Web Text))

Max Activating Token Index: 390