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

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

Neuron 3487 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2710. Min Range: -3.2710

Max Act: 3.2710. Min Act: -0.0000

Data Index: 1037379 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 3.2710. Min Range: -3.2710

Max Act: 2.8445. Min Act: -0.0000

Data Index: 1217482 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 3.2710. Min Range: -3.2710

Max Act: 2.4721. Min Act: -0.0000

Data Index: 625205 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 3.2710. Min Range: -3.2710

Max Act: 2.4046. Min Act: -0.0000

Data Index: 1259459 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 3.2710. Min Range: -3.2710

Max Act: 2.3837. Min Act: -0.0000

Data Index: 497614 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 3.2710. Min Range: -3.2710

Max Act: 2.2565. Min Act: -0.0000

Data Index: 192747 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 3.2710. Min Range: -3.2710

Max Act: 2.1654. Min Act: -0.0000

Data Index: 401138 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 3.2710. Min Range: -3.2710

Max Act: 2.3487. Min Act: -0.0000

Data Index: 739894 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 3.2710. Min Range: -3.2710

Max Act: 2.2905. Min Act: -0.0000

Data Index: 180477 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 3.2710. Min Range: -3.2710

Max Act: 2.3169. Min Act: -0.0000

Data Index: 805452 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 3.2710. Min Range: -3.2710

Max Act: 2.0603. Min Act: -0.0000

Data Index: 1035090 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 3.2710. Min Range: -3.2710

Max Act: 2.1412. Min Act: -0.0000

Data Index: 17228 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 3.2710. Min Range: -3.2710

Max Act: 2.1394. Min Act: -0.0000

Data Index: 850390 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 3.2710. Min Range: -3.2710

Max Act: 2.0368. Min Act: -0.0000

Data Index: 1284807 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 3.2710. Min Range: -3.2710

Max Act: 2.0141. Min Act: -0.0001

Data Index: 341680 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 3.2710. Min Range: -3.2710

Max Act: 1.9720. Min Act: -0.0000

Data Index: 936679 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 3.2710. Min Range: -3.2710

Max Act: 1.9452. Min Act: -0.0000

Data Index: 1205624 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 3.2710. Min Range: -3.2710

Max Act: 2.0508. Min Act: -0.0000

Data Index: 1063847 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 3.2710. Min Range: -3.2710

Max Act: 2.3493. Min Act: -0.0000

Data Index: 825675 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 3.2710. Min Range: -3.2710

Max Act: 1.8892. Min Act: -0.0000

Data Index: 748232 (C4 (Web Text))

Max Activating Token Index: 220