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

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

Neuron 3187 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9693. Min Range: -5.9693

Max Act: 5.9693. Min Act: -0.0000

Data Index: 1212835 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 5.9693. Min Range: -5.9693

Max Act: 5.2632. Min Act: -0.0000

Data Index: 341124 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 5.9693. Min Range: -5.9693

Max Act: 5.1308. Min Act: -0.0000

Data Index: 1200554 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 5.9693. Min Range: -5.9693

Max Act: 4.5593. Min Act: -0.0000

Data Index: 1135328 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 5.9693. Min Range: -5.9693

Max Act: 4.2131. Min Act: -0.0000

Data Index: 495586 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 5.9693. Min Range: -5.9693

Max Act: 4.3480. Min Act: -0.0000

Data Index: 1089828 (C4 (Web Text))

Max Activating Token Index: 393

Text #6

Max Range: 5.9693. Min Range: -5.9693

Max Act: 4.3715. Min Act: -0.0000

Data Index: 1254205 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 5.9693. Min Range: -5.9693

Max Act: 4.2682. Min Act: -0.0000

Data Index: 1335615 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 5.9693. Min Range: -5.9693

Max Act: 4.1845. Min Act: -0.0000

Data Index: 1250810 (C4 (Web Text))

Max Activating Token Index: 966

Text #9

Max Range: 5.9693. Min Range: -5.9693

Max Act: 4.0599. Min Act: -0.0000

Data Index: 40784 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 5.9693. Min Range: -5.9693

Max Act: 3.8816. Min Act: -0.0000

Data Index: 1324345 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 5.9693. Min Range: -5.9693

Max Act: 3.7041. Min Act: -0.0000

Data Index: 53594 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 5.9693. Min Range: -5.9693

Max Act: 3.6675. Min Act: -0.0000

Data Index: 451428 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 5.9693. Min Range: -5.9693

Max Act: 3.7897. Min Act: -0.0000

Data Index: 916373 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 5.9693. Min Range: -5.9693

Max Act: 3.9514. Min Act: -0.0000

Data Index: 727080 (C4 (Web Text))

Max Activating Token Index: 930

Text #15

Max Range: 5.9693. Min Range: -5.9693

Max Act: 3.9444. Min Act: -0.0000

Data Index: 379434 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 5.9693. Min Range: -5.9693

Max Act: 3.4595. Min Act: -0.0000

Data Index: 1094906 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 5.9693. Min Range: -5.9693

Max Act: 3.6778. Min Act: -0.0000

Data Index: 18755 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 5.9693. Min Range: -5.9693

Max Act: 3.3594. Min Act: -0.0000

Data Index: 965378 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 5.9693. Min Range: -5.9693

Max Act: 3.4918. Min Act: -0.0000

Data Index: 41393 (C4 (Web Text))

Max Activating Token Index: 301