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

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

Neuron 1904 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.7434. Min Act: -0.0000

Data Index: 562041 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.5897. Min Act: -0.0000

Data Index: 418083 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.6071. Min Act: -0.0000

Data Index: 313762 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.5692. Min Act: -0.0000

Data Index: 602998 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.5119. Min Act: -0.0000

Data Index: 589918 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.4985. Min Act: -0.0000

Data Index: 819899 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.5155. Min Act: -0.0000

Data Index: 28779 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.5316. Min Act: -0.0000

Data Index: 968561 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.5039. Min Act: -0.0000

Data Index: 1330038 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.5480. Min Act: -0.0000

Data Index: 646427 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.4968. Min Act: -0.0000

Data Index: 939242 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.4887. Min Act: -0.0000

Data Index: 295615 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.4710. Min Act: -0.0000

Data Index: 1201976 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.4309. Min Act: -0.0000

Data Index: 1312250 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.4421. Min Act: -0.0000

Data Index: 1335220 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.4642. Min Act: -0.0000

Data Index: 677154 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.4451. Min Act: -0.0000

Data Index: 15784 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.4325. Min Act: -0.0000

Data Index: 306508 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.4608. Min Act: -0.0000

Data Index: 460244 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 0.7434. Min Range: -0.7434

Max Act: 0.4287. Min Act: -0.0000

Data Index: 788226 (C4 (Web Text))

Max Activating Token Index: 17