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

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

Neuron 43 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2064. Min Range: -4.2064

Max Act: 4.0749. Min Act: -0.0000

Data Index: 292030 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 4.2064. Min Range: -4.2064

Max Act: 4.0510. Min Act: -0.0000

Data Index: 107359 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 4.2064. Min Range: -4.2064

Max Act: 4.2064. Min Act: -0.0000

Data Index: 24244 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 4.2064. Min Range: -4.2064

Max Act: 3.9246. Min Act: -0.0000

Data Index: 648244 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 4.2064. Min Range: -4.2064

Max Act: 3.8790. Min Act: -0.0000

Data Index: 1317123 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 4.2064. Min Range: -4.2064

Max Act: 3.8272. Min Act: -0.0000

Data Index: 1096677 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 4.2064. Min Range: -4.2064

Max Act: 4.0019. Min Act: -0.0000

Data Index: 193585 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 4.2064. Min Range: -4.2064

Max Act: 3.9453. Min Act: -0.0000

Data Index: 538461 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 4.2064. Min Range: -4.2064

Max Act: 3.5965. Min Act: -0.0000

Data Index: 812870 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 4.2064. Min Range: -4.2064

Max Act: 3.7909. Min Act: -0.0000

Data Index: 604274 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 4.2064. Min Range: -4.2064

Max Act: 3.9361. Min Act: -0.0000

Data Index: 1293139 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 4.2064. Min Range: -4.2064

Max Act: 3.8526. Min Act: -0.0000

Data Index: 782645 (C4 (Web Text))

Max Activating Token Index: 709

Text #12

Max Range: 4.2064. Min Range: -4.2064

Max Act: 3.6506. Min Act: -0.0000

Data Index: 978151 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 4.2064. Min Range: -4.2064

Max Act: 3.6568. Min Act: -0.0000

Data Index: 1291648 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 4.2064. Min Range: -4.2064

Max Act: 3.6053. Min Act: -0.0000

Data Index: 582528 (C4 (Web Text))

Max Activating Token Index: 481

Text #15

Max Range: 4.2064. Min Range: -4.2064

Max Act: 3.5950. Min Act: -0.0000

Data Index: 506088 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 4.2064. Min Range: -4.2064

Max Act: 3.7224. Min Act: -0.0000

Data Index: 411641 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 4.2064. Min Range: -4.2064

Max Act: 3.5344. Min Act: -0.0000

Data Index: 968471 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 4.2064. Min Range: -4.2064

Max Act: 3.5022. Min Act: -0.0000

Data Index: 119700 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 4.2064. Min Range: -4.2064

Max Act: 3.4801. Min Act: -0.0000

Data Index: 418727 (C4 (Web Text))

Max Activating Token Index: 721