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

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

Neuron 328 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4586. Min Range: -4.4586

Max Act: 4.4586. Min Act: -0.0000

Data Index: 410027 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 4.4586. Min Range: -4.4586

Max Act: 4.2565. Min Act: -0.0000

Data Index: 882583 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 4.4586. Min Range: -4.4586

Max Act: 3.8149. Min Act: -0.0000

Data Index: 766228 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 4.4586. Min Range: -4.4586

Max Act: 3.4748. Min Act: -0.0000

Data Index: 56963 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 4.4586. Min Range: -4.4586

Max Act: 3.1816. Min Act: -0.0000

Data Index: 1087780 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 4.4586. Min Range: -4.4586

Max Act: 3.1368. Min Act: -0.0000

Data Index: 90528 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 4.4586. Min Range: -4.4586

Max Act: 2.5933. Min Act: -0.0000

Data Index: 39986 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 4.4586. Min Range: -4.4586

Max Act: 2.8240. Min Act: -0.0000

Data Index: 406301 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 4.4586. Min Range: -4.4586

Max Act: 2.3820. Min Act: -0.0000

Data Index: 292723 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 4.4586. Min Range: -4.4586

Max Act: 2.7358. Min Act: -0.0000

Data Index: 1015360 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 4.4586. Min Range: -4.4586

Max Act: 2.2568. Min Act: -0.0000

Data Index: 702404 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 4.4586. Min Range: -4.4586

Max Act: 2.7688. Min Act: -0.0000

Data Index: 365474 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 4.4586. Min Range: -4.4586

Max Act: 2.5523. Min Act: -0.0000

Data Index: 1006161 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 4.4586. Min Range: -4.4586

Max Act: 2.5478. Min Act: -0.0000

Data Index: 1367240 (Python Code)

Max Activating Token Index: 237

Text #14

Max Range: 4.4586. Min Range: -4.4586

Max Act: 2.4901. Min Act: -0.0000

Data Index: 226766 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 4.4586. Min Range: -4.4586

Max Act: 2.4515. Min Act: -0.0000

Data Index: 1269297 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 4.4586. Min Range: -4.4586

Max Act: 2.8327. Min Act: -0.0000

Data Index: 631520 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 4.4586. Min Range: -4.4586

Max Act: 2.2640. Min Act: -0.0000

Data Index: 852614 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 4.4586. Min Range: -4.4586

Max Act: 2.3752. Min Act: -0.0000

Data Index: 800696 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 4.4586. Min Range: -4.4586

Max Act: 2.3558. Min Act: -0.0000

Data Index: 1233382 (C4 (Web Text))

Max Activating Token Index: 243