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

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

Neuron 3000 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.7610. Min Act: -0.0000

Data Index: 1177087 (C4 (Web Text))

Max Activating Token Index: 367

Text #1

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.6840. Min Act: -0.0000

Data Index: 950223 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.6954. Min Act: -0.0000

Data Index: 808522 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.6111. Min Act: -0.0000

Data Index: 115980 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.6244. Min Act: -0.0000

Data Index: 731062 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.6373. Min Act: -0.0000

Data Index: 434393 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.5986. Min Act: -0.0000

Data Index: 869450 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.5949. Min Act: -0.0000

Data Index: 324587 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.5431. Min Act: -0.0000

Data Index: 1210243 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.5422. Min Act: -0.0000

Data Index: 1014716 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.5482. Min Act: -0.0001

Data Index: 528373 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.5127. Min Act: -0.0000

Data Index: 1334634 (C4 (Web Text))

Max Activating Token Index: 619

Text #12

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.5549. Min Act: -0.0000

Data Index: 1154439 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.5340. Min Act: -0.0000

Data Index: 308079 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.5684. Min Act: -0.0000

Data Index: 1211116 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.5173. Min Act: -0.0000

Data Index: 882433 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.5310. Min Act: -0.0000

Data Index: 972877 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.5276. Min Act: -0.0000

Data Index: 263984 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.5233. Min Act: -0.0000

Data Index: 895120 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 0.7610. Min Range: -0.7610

Max Act: 0.5229. Min Act: -0.0000

Data Index: 1001994 (C4 (Web Text))

Max Activating Token Index: 972