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

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

Neuron 3318 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2996. Min Range: -3.2996

Max Act: 3.2996. Min Act: -0.0001

Data Index: 146522 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 3.2996. Min Range: -3.2996

Max Act: 2.4888. Min Act: -0.0001

Data Index: 1014757 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 3.2996. Min Range: -3.2996

Max Act: 2.3725. Min Act: -0.0001

Data Index: 887770 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 3.2996. Min Range: -3.2996

Max Act: 2.0931. Min Act: -0.0001

Data Index: 676632 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 3.2996. Min Range: -3.2996

Max Act: 1.9969. Min Act: -0.0001

Data Index: 551972 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 3.2996. Min Range: -3.2996

Max Act: 1.7252. Min Act: -0.0001

Data Index: 1019693 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 3.2996. Min Range: -3.2996

Max Act: 1.8550. Min Act: -0.0001

Data Index: 1355055 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 3.2996. Min Range: -3.2996

Max Act: 1.7272. Min Act: -0.0001

Data Index: 147234 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 3.2996. Min Range: -3.2996

Max Act: 1.5881. Min Act: -0.0001

Data Index: 1255118 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 3.2996. Min Range: -3.2996

Max Act: 1.6656. Min Act: -0.0001

Data Index: 925010 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 3.2996. Min Range: -3.2996

Max Act: 1.4647. Min Act: -0.0001

Data Index: 854291 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 3.2996. Min Range: -3.2996

Max Act: 1.4703. Min Act: -0.0001

Data Index: 270014 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 3.2996. Min Range: -3.2996

Max Act: 1.3546. Min Act: -0.0001

Data Index: 764702 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 3.2996. Min Range: -3.2996

Max Act: 1.4222. Min Act: -0.0001

Data Index: 569205 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 3.2996. Min Range: -3.2996

Max Act: 1.4104. Min Act: -0.0001

Data Index: 32509 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 3.2996. Min Range: -3.2996

Max Act: 1.3580. Min Act: -0.0001

Data Index: 816120 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 3.2996. Min Range: -3.2996

Max Act: 1.3328. Min Act: -0.0001

Data Index: 469761 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 3.2996. Min Range: -3.2996

Max Act: 1.3377. Min Act: -0.0001

Data Index: 189732 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 3.2996. Min Range: -3.2996

Max Act: 1.3239. Min Act: -0.0001

Data Index: 721399 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 3.2996. Min Range: -3.2996

Max Act: 1.3219. Min Act: -0.0001

Data Index: 265036 (C4 (Web Text))

Max Activating Token Index: 119