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

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

Neuron 3008 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0547. Min Range: -3.0547

Max Act: 3.0547. Min Act: -0.0000

Data Index: 177974 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 3.0547. Min Range: -3.0547

Max Act: 2.7555. Min Act: -0.0000

Data Index: 216170 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 3.0547. Min Range: -3.0547

Max Act: 2.5465. Min Act: -0.0000

Data Index: 848592 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 3.0547. Min Range: -3.0547

Max Act: 2.5088. Min Act: -0.0000

Data Index: 150346 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 3.0547. Min Range: -3.0547

Max Act: 2.5143. Min Act: -0.0000

Data Index: 1272158 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 3.0547. Min Range: -3.0547

Max Act: 1.8677. Min Act: -0.0000

Data Index: 225433 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 3.0547. Min Range: -3.0547

Max Act: 2.3312. Min Act: -0.0000

Data Index: 1016667 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 3.0547. Min Range: -3.0547

Max Act: 2.3015. Min Act: -0.0000

Data Index: 186716 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 3.0547. Min Range: -3.0547

Max Act: 2.4221. Min Act: -0.0000

Data Index: 1323556 (C4 (Web Text))

Max Activating Token Index: 491

Text #9

Max Range: 3.0547. Min Range: -3.0547

Max Act: 2.5446. Min Act: -0.0000

Data Index: 58785 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 3.0547. Min Range: -3.0547

Max Act: 2.4211. Min Act: -0.0000

Data Index: 158695 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 3.0547. Min Range: -3.0547

Max Act: 2.2833. Min Act: -0.0000

Data Index: 1133060 (C4 (Web Text))

Max Activating Token Index: 773

Text #12

Max Range: 3.0547. Min Range: -3.0547

Max Act: 2.1445. Min Act: -0.0000

Data Index: 964230 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 3.0547. Min Range: -3.0547

Max Act: 2.6563. Min Act: -0.0000

Data Index: 1302454 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 3.0547. Min Range: -3.0547

Max Act: 2.2533. Min Act: -0.0000

Data Index: 337751 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 3.0547. Min Range: -3.0547

Max Act: 2.4293. Min Act: -0.0000

Data Index: 735192 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 3.0547. Min Range: -3.0547

Max Act: 2.1815. Min Act: -0.0000

Data Index: 434460 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 3.0547. Min Range: -3.0547

Max Act: 2.2950. Min Act: -0.0000

Data Index: 1168120 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 3.0547. Min Range: -3.0547

Max Act: 2.1618. Min Act: -0.0000

Data Index: 130019 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 3.0547. Min Range: -3.0547

Max Act: 2.3554. Min Act: -0.0000

Data Index: 1343919 (C4 (Web Text))

Max Activating Token Index: 53