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

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

Neuron 5726 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0587. Min Range: -5.0587

Max Act: 4.9540. Min Act: -0.0000

Data Index: 408217 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 5.0587. Min Range: -5.0587

Max Act: 4.6923. Min Act: -0.0000

Data Index: 952860 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 5.0587. Min Range: -5.0587

Max Act: 4.6120. Min Act: -0.0000

Data Index: 1342709 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 5.0587. Min Range: -5.0587

Max Act: 5.0587. Min Act: -0.0000

Data Index: 1335710 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 5.0587. Min Range: -5.0587

Max Act: 4.0216. Min Act: -0.0000

Data Index: 27391 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 5.0587. Min Range: -5.0587

Max Act: 4.0048. Min Act: -0.0000

Data Index: 147505 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 5.0587. Min Range: -5.0587

Max Act: 3.9420. Min Act: -0.0000

Data Index: 551590 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 5.0587. Min Range: -5.0587

Max Act: 3.8073. Min Act: -0.0000

Data Index: 1039026 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 5.0587. Min Range: -5.0587

Max Act: 3.4960. Min Act: -0.0000

Data Index: 1268074 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 5.0587. Min Range: -5.0587

Max Act: 3.5032. Min Act: -0.0000

Data Index: 992131 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 5.0587. Min Range: -5.0587

Max Act: 3.4444. Min Act: -0.0000

Data Index: 821625 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 5.0587. Min Range: -5.0587

Max Act: 3.2606. Min Act: -0.0000

Data Index: 203045 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 5.0587. Min Range: -5.0587

Max Act: 3.5586. Min Act: -0.0000

Data Index: 1281328 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 5.0587. Min Range: -5.0587

Max Act: 2.9133. Min Act: -0.0000

Data Index: 282667 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 5.0587. Min Range: -5.0587

Max Act: 3.2086. Min Act: -0.0000

Data Index: 28910 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 5.0587. Min Range: -5.0587

Max Act: 3.0589. Min Act: -0.0000

Data Index: 1311379 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 5.0587. Min Range: -5.0587

Max Act: 3.3092. Min Act: -0.0000

Data Index: 29181 (C4 (Web Text))

Max Activating Token Index: 277

Text #17

Max Range: 5.0587. Min Range: -5.0587

Max Act: 2.9855. Min Act: -0.0000

Data Index: 1163751 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 5.0587. Min Range: -5.0587

Max Act: 3.0865. Min Act: -0.0000

Data Index: 742827 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 5.0587. Min Range: -5.0587

Max Act: 3.2366. Min Act: -0.0000

Data Index: 56917 (C4 (Web Text))

Max Activating Token Index: 60