Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5266 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.9347. Min Act: -0.0000

Data Index: 650505 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.9800. Min Act: -0.0000

Data Index: 550122 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.8730. Min Act: -0.0000

Data Index: 1292650 (C4 (Web Text))

Max Activating Token Index: 361

Text #3

Max Range: 2.0957. Min Range: -2.0957

Max Act: 2.0957. Min Act: -0.0000

Data Index: 1245074 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.8622. Min Act: -0.0000

Data Index: 1287036 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.7571. Min Act: -0.0000

Data Index: 684222 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.8104. Min Act: -0.0000

Data Index: 363855 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.6444. Min Act: -0.0000

Data Index: 11268 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.7257. Min Act: -0.0000

Data Index: 325568 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.7260. Min Act: -0.0000

Data Index: 195291 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.7090. Min Act: -0.0000

Data Index: 374878 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.6042. Min Act: -0.0000

Data Index: 194440 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.7809. Min Act: -0.0000

Data Index: 1218745 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.6463. Min Act: -0.0000

Data Index: 6361 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.6607. Min Act: -0.0000

Data Index: 588866 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.5132. Min Act: -0.0000

Data Index: 1176769 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.6092. Min Act: -0.0000

Data Index: 834688 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.5967. Min Act: -0.0000

Data Index: 1163387 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.4825. Min Act: -0.0000

Data Index: 672675 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.5290. Min Act: -0.0000

Data Index: 130538 (C4 (Web Text))

Max Activating Token Index: 880