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

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

Neuron 4017 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.6702. Min Act: -0.0000

Data Index: 464012 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.6430. Min Act: -0.0000

Data Index: 157655 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.6369. Min Act: -0.0000

Data Index: 899394 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.6309. Min Act: -0.0000

Data Index: 64628 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.6006. Min Act: -0.0000

Data Index: 1305652 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.5779. Min Act: -0.0000

Data Index: 568683 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.5786. Min Act: -0.0000

Data Index: 295399 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.5868. Min Act: -0.0000

Data Index: 1203099 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.5749. Min Act: -0.0000

Data Index: 1043945 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.5919. Min Act: -0.0000

Data Index: 7318 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.5708. Min Act: -0.0000

Data Index: 1440709 (Python Code)

Max Activating Token Index: 86

Text #11

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.5286. Min Act: -0.0000

Data Index: 289800 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.5451. Min Act: -0.0000

Data Index: 1358553 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.5505. Min Act: -0.0000

Data Index: 723190 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.5416. Min Act: -0.0000

Data Index: 882821 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.5380. Min Act: -0.0000

Data Index: 76773 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.5369. Min Act: -0.0000

Data Index: 357042 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4865. Min Act: -0.0000

Data Index: 819819 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.5397. Min Act: -0.0000

Data Index: 1518 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.5366. Min Act: -0.0000

Data Index: 782726 (C4 (Web Text))

Max Activating Token Index: 214