Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2645 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.7089. Min Act: -0.0001

Data Index: 1377063 (Python Code)

Max Activating Token Index: 45

Text #1

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.6459. Min Act: -0.0001

Data Index: 1596719 (Python Code)

Max Activating Token Index: 303

Text #2

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.6230. Min Act: -0.0001

Data Index: 1032536 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.6408. Min Act: -0.0001

Data Index: 1462007 (Python Code)

Max Activating Token Index: 61

Text #4

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.6423. Min Act: -0.0001

Data Index: 1515954 (Python Code)

Max Activating Token Index: 24

Text #5

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.6172. Min Act: -0.0001

Data Index: 1441704 (Python Code)

Max Activating Token Index: 432

Text #6

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.6241. Min Act: -0.0001

Data Index: 1623672 (Python Code)

Max Activating Token Index: 109

Text #7

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.6284. Min Act: -0.0001

Data Index: 1423810 (Python Code)

Max Activating Token Index: 98

Text #8

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.6054. Min Act: -0.0001

Data Index: 1369610 (Python Code)

Max Activating Token Index: 539

Text #9

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.6085. Min Act: -0.0001

Data Index: 1479787 (Python Code)

Max Activating Token Index: 103

Text #10

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.6331. Min Act: -0.0001

Data Index: 1360531 (Python Code)

Max Activating Token Index: 105

Text #11

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.5988. Min Act: -0.0001

Data Index: 1647857 (Python Code)

Max Activating Token Index: 386

Text #12

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.5813. Min Act: -0.0001

Data Index: 1629794 (Python Code)

Max Activating Token Index: 11

Text #13

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.5316. Min Act: -0.0001

Data Index: 493281 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.5396. Min Act: -0.0001

Data Index: 89308 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.6075. Min Act: -0.0001

Data Index: 317413 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.5673. Min Act: -0.0001

Data Index: 1134005 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.5876. Min Act: -0.0001

Data Index: 283047 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.5164. Min Act: -0.0001

Data Index: 678232 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.5652. Min Act: -0.0001

Data Index: 1451639 (Python Code)

Max Activating Token Index: 436