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

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

Neuron 5082 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: 0.5321. Min Range: -0.5321

Max Act: 0.5321. Min Act: -0.0000

Data Index: 1247839 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4534. Min Act: -0.0000

Data Index: 52902 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4516. Min Act: -0.0000

Data Index: 1315806 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4263. Min Act: -0.0000

Data Index: 798200 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4339. Min Act: -0.0000

Data Index: 1112969 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.3947. Min Act: -0.0000

Data Index: 706720 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.3928. Min Act: -0.0000

Data Index: 269342 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.3657. Min Act: -0.0000

Data Index: 1265268 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.3689. Min Act: -0.0000

Data Index: 1197275 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.3682. Min Act: -0.0000

Data Index: 130886 (C4 (Web Text))

Max Activating Token Index: 703

Text #10

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.3727. Min Act: -0.0000

Data Index: 1116156 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.3668. Min Act: -0.0000

Data Index: 305196 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.3493. Min Act: -0.0000

Data Index: 846735 (C4 (Web Text))

Max Activating Token Index: 921

Text #13

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.3347. Min Act: -0.0000

Data Index: 482378 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.3530. Min Act: -0.0000

Data Index: 1299258 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.3468. Min Act: -0.0000

Data Index: 175412 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.3271. Min Act: -0.0000

Data Index: 842351 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.3473. Min Act: -0.0000

Data Index: 198608 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.3353. Min Act: -0.0000

Data Index: 1278079 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.3359. Min Act: -0.0000

Data Index: 316565 (C4 (Web Text))

Max Activating Token Index: 986