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

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

Neuron 5460 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.8457. Min Act: -0.0000

Data Index: 802447 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.8307. Min Act: -0.0000

Data Index: 896640 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.7981. Min Act: -0.0000

Data Index: 86591 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.7747. Min Act: -0.0000

Data Index: 460601 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.7725. Min Act: -0.0000

Data Index: 439781 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.8025. Min Act: -0.0000

Data Index: 209918 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.7188. Min Act: -0.0000

Data Index: 387664 (C4 (Web Text))

Max Activating Token Index: 903

Text #7

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.7674. Min Act: -0.0000

Data Index: 147615 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.7388. Min Act: -0.0000

Data Index: 536706 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.7890. Min Act: -0.0000

Data Index: 442048 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.7346. Min Act: -0.0000

Data Index: 720247 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.7298. Min Act: -0.0000

Data Index: 995568 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.7691. Min Act: -0.0000

Data Index: 924503 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.6964. Min Act: -0.0000

Data Index: 616081 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.7180. Min Act: -0.0000

Data Index: 231643 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.7397. Min Act: -0.0000

Data Index: 616538 (C4 (Web Text))

Max Activating Token Index: 941

Text #16

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.7295. Min Act: -0.0000

Data Index: 845692 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.6911. Min Act: -0.0000

Data Index: 1059998 (C4 (Web Text))

Max Activating Token Index: 342

Text #18

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.6468. Min Act: -0.0000

Data Index: 1154180 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.6975. Min Act: -0.0000

Data Index: 744136 (C4 (Web Text))

Max Activating Token Index: 173