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

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

Neuron 1353 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.9798. Min Act: -0.0001

Data Index: 1509124 (Python Code)

Max Activating Token Index: 216

Text #1

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.9494. Min Act: -0.0001

Data Index: 1645157 (Python Code)

Max Activating Token Index: 988

Text #2

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.9988. Min Act: -0.0001

Data Index: 1654537 (Python Code)

Max Activating Token Index: 179

Text #3

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.8662. Min Act: -0.0001

Data Index: 1564566 (Python Code)

Max Activating Token Index: 966

Text #4

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.7685. Min Act: -0.0001

Data Index: 1189529 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.4869. Min Act: -0.0001

Data Index: 448144 (C4 (Web Text))

Max Activating Token Index: 603

Text #6

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.7208. Min Act: -0.0001

Data Index: 1365630 (Python Code)

Max Activating Token Index: 7

Text #7

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.8417. Min Act: -0.0001

Data Index: 1222543 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.7648. Min Act: -0.0001

Data Index: 850201 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.7240. Min Act: -0.0001

Data Index: 1478422 (Python Code)

Max Activating Token Index: 376

Text #10

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.6243. Min Act: -0.0001

Data Index: 548808 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.5163. Min Act: -0.0001

Data Index: 746530 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.7022. Min Act: -0.0001

Data Index: 39669 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.5878. Min Act: -0.0001

Data Index: 1257433 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.4841. Min Act: -0.0001

Data Index: 251379 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.5754. Min Act: -0.0001

Data Index: 528760 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.5080. Min Act: -0.0001

Data Index: 771554 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.4580. Min Act: -0.0001

Data Index: 55526 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.5289. Min Act: -0.0001

Data Index: 1277446 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.4242. Min Act: -0.0001

Data Index: 845892 (C4 (Web Text))

Max Activating Token Index: 397