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

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

Neuron 2398 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: 7.6711. Min Range: -7.6711

Max Act: 7.6711. Min Act: -0.0000

Data Index: 308181 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 7.6711. Min Range: -7.6711

Max Act: 5.5453. Min Act: -0.0000

Data Index: 33816 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 7.6711. Min Range: -7.6711

Max Act: 5.5615. Min Act: -0.0000

Data Index: 674320 (C4 (Web Text))

Max Activating Token Index: 627

Text #3

Max Range: 7.6711. Min Range: -7.6711

Max Act: 5.7388. Min Act: -0.0000

Data Index: 163173 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 7.6711. Min Range: -7.6711

Max Act: 5.0751. Min Act: -0.0000

Data Index: 1114589 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 7.6711. Min Range: -7.6711

Max Act: 4.4921. Min Act: -0.0000

Data Index: 967863 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 7.6711. Min Range: -7.6711

Max Act: 4.8105. Min Act: -0.0000

Data Index: 1015335 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 7.6711. Min Range: -7.6711

Max Act: 4.6967. Min Act: -0.0000

Data Index: 1104068 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 7.6711. Min Range: -7.6711

Max Act: 4.4822. Min Act: -0.0000

Data Index: 910149 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 7.6711. Min Range: -7.6711

Max Act: 4.4287. Min Act: -0.0000

Data Index: 397352 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 7.6711. Min Range: -7.6711

Max Act: 4.2188. Min Act: -0.0000

Data Index: 643751 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 7.6711. Min Range: -7.6711

Max Act: 4.3406. Min Act: -0.0000

Data Index: 782717 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 7.6711. Min Range: -7.6711

Max Act: 4.4713. Min Act: -0.0000

Data Index: 767166 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 7.6711. Min Range: -7.6711

Max Act: 4.4917. Min Act: -0.0000

Data Index: 435104 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 7.6711. Min Range: -7.6711

Max Act: 4.4471. Min Act: -0.0000

Data Index: 795040 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 7.6711. Min Range: -7.6711

Max Act: 4.2480. Min Act: -0.0000

Data Index: 29156 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 7.6711. Min Range: -7.6711

Max Act: 4.2328. Min Act: -0.0000

Data Index: 434499 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 7.6711. Min Range: -7.6711

Max Act: 4.2093. Min Act: -0.0000

Data Index: 951746 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 7.6711. Min Range: -7.6711

Max Act: 4.0044. Min Act: -0.0000

Data Index: 973994 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 7.6711. Min Range: -7.6711

Max Act: 4.1520. Min Act: -0.0000

Data Index: 34573 (C4 (Web Text))

Max Activating Token Index: 838