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

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

Neuron 3035 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: 0.6378. Min Range: -0.6378

Max Act: 0.6378. Min Act: -0.0000

Data Index: 163407 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.5929. Min Act: -0.0000

Data Index: 831678 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.5545. Min Act: -0.0000

Data Index: 709215 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.5518. Min Act: -0.0000

Data Index: 803779 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.5177. Min Act: -0.0000

Data Index: 301349 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.5577. Min Act: -0.0000

Data Index: 351624 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.5341. Min Act: -0.0000

Data Index: 249517 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.4821. Min Act: -0.0000

Data Index: 1120206 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.5342. Min Act: -0.0000

Data Index: 935896 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.5166. Min Act: -0.0000

Data Index: 243932 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.4895. Min Act: -0.0000

Data Index: 1069922 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.4988. Min Act: -0.0000

Data Index: 1303128 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.5000. Min Act: -0.0000

Data Index: 377214 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.5057. Min Act: -0.0000

Data Index: 768075 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.4910. Min Act: -0.0000

Data Index: 311767 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.4923. Min Act: -0.0000

Data Index: 812585 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.4810. Min Act: -0.0000

Data Index: 772332 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.4280. Min Act: -0.0000

Data Index: 1038011 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.4403. Min Act: -0.0000

Data Index: 670670 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.4214. Min Act: -0.0000

Data Index: 622465 (C4 (Web Text))

Max Activating Token Index: 119