Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 19 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.8412. Min Act: -0.0001

Data Index: 827782 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6829. Min Act: -0.0001

Data Index: 213160 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6044. Min Act: -0.0001

Data Index: 740923 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6984. Min Act: -0.0001

Data Index: 483011 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6433. Min Act: -0.0001

Data Index: 1033858 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6190. Min Act: -0.0001

Data Index: 677320 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6349. Min Act: -0.0001

Data Index: 145882 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.5898. Min Act: -0.0001

Data Index: 305253 (C4 (Web Text))

Max Activating Token Index: 487

Text #8

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.5485. Min Act: -0.0001

Data Index: 302730 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6006. Min Act: -0.0001

Data Index: 812202 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.5977. Min Act: -0.0001

Data Index: 561645 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.5748. Min Act: -0.0001

Data Index: 845316 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.5516. Min Act: -0.0001

Data Index: 543116 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.5140. Min Act: -0.0001

Data Index: 1027948 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.5725. Min Act: -0.0001

Data Index: 659658 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.5253. Min Act: -0.0001

Data Index: 767796 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.5774. Min Act: -0.0001

Data Index: 759687 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.3994. Min Act: -0.0001

Data Index: 193550 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.5129. Min Act: -0.0001

Data Index: 715562 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.5422. Min Act: -0.0001

Data Index: 376424 (C4 (Web Text))

Max Activating Token Index: 551