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

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

Neuron 4337 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9475. Min Range: -5.9475

Max Act: 5.9475. Min Act: -0.0000

Data Index: 1135570 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 5.9475. Min Range: -5.9475

Max Act: 5.5873. Min Act: -0.0000

Data Index: 1123855 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 5.9475. Min Range: -5.9475

Max Act: 5.3125. Min Act: -0.0000

Data Index: 1039696 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 5.9475. Min Range: -5.9475

Max Act: 5.3526. Min Act: -0.0000

Data Index: 83153 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 5.9475. Min Range: -5.9475

Max Act: 5.4061. Min Act: -0.0000

Data Index: 632961 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 5.9475. Min Range: -5.9475

Max Act: 5.0261. Min Act: -0.0000

Data Index: 183354 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 5.9475. Min Range: -5.9475

Max Act: 4.9497. Min Act: -0.0000

Data Index: 133020 (C4 (Web Text))

Max Activating Token Index: 1012

Text #7

Max Range: 5.9475. Min Range: -5.9475

Max Act: 4.9587. Min Act: -0.0000

Data Index: 68182 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 5.9475. Min Range: -5.9475

Max Act: 4.7267. Min Act: -0.0000

Data Index: 482074 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 5.9475. Min Range: -5.9475

Max Act: 5.2700. Min Act: -0.0000

Data Index: 1070448 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 5.9475. Min Range: -5.9475

Max Act: 5.0888. Min Act: -0.0000

Data Index: 1129362 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 5.9475. Min Range: -5.9475

Max Act: 5.0537. Min Act: -0.0000

Data Index: 1196732 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 5.9475. Min Range: -5.9475

Max Act: 5.0670. Min Act: -0.0000

Data Index: 1096916 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 5.9475. Min Range: -5.9475

Max Act: 4.8357. Min Act: -0.0000

Data Index: 663836 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 5.9475. Min Range: -5.9475

Max Act: 4.8326. Min Act: -0.0000

Data Index: 1072412 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 5.9475. Min Range: -5.9475

Max Act: 4.6475. Min Act: -0.0000

Data Index: 1307377 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 5.9475. Min Range: -5.9475

Max Act: 4.6438. Min Act: -0.0000

Data Index: 324988 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 5.9475. Min Range: -5.9475

Max Act: 4.2034. Min Act: -0.0000

Data Index: 645652 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 5.9475. Min Range: -5.9475

Max Act: 4.2783. Min Act: -0.0000

Data Index: 710558 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 5.9475. Min Range: -5.9475

Max Act: 3.9001. Min Act: -0.0000

Data Index: 158169 (C4 (Web Text))

Max Activating Token Index: 298