Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2575 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.5642. Min Act: -0.0000

Data Index: 123964 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.5966. Min Act: -0.0001

Data Index: 1264417 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.4951. Min Act: -0.0000

Data Index: 1342356 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.4258. Min Act: -0.0000

Data Index: 1149727 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.3896. Min Act: -0.0000

Data Index: 413555 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.3803. Min Act: -0.0001

Data Index: 971720 (C4 (Web Text))

Max Activating Token Index: 321

Text #6

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.3650. Min Act: -0.0000

Data Index: 229204 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.3459. Min Act: -0.0000

Data Index: 1350755 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.3647. Min Act: -0.0000

Data Index: 128146 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.3538. Min Act: -0.0000

Data Index: 600725 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.3419. Min Act: 0.0000

Data Index: 1241006 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.3241. Min Act: -0.0000

Data Index: 1303783 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.3353. Min Act: -0.0000

Data Index: 221583 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.3135. Min Act: -0.0001

Data Index: 805182 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.3064. Min Act: -0.0000

Data Index: 1207189 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.3131. Min Act: -0.0000

Data Index: 1300991 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.3096. Min Act: -0.0000

Data Index: 1164231 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.3171. Min Act: -0.0001

Data Index: 662714 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.3041. Min Act: -0.0001

Data Index: 564185 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.3281. Min Act: -0.0001

Data Index: 438846 (C4 (Web Text))

Max Activating Token Index: 573