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

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

Neuron 5777 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1325. Min Range: -2.1325

Max Act: 2.1325. Min Act: -0.0000

Data Index: 1201451 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 2.1325. Min Range: -2.1325

Max Act: 1.5868. Min Act: -0.0000

Data Index: 213420 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 2.1325. Min Range: -2.1325

Max Act: 1.6537. Min Act: -0.0000

Data Index: 1086025 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 2.1325. Min Range: -2.1325

Max Act: 1.4338. Min Act: -0.0000

Data Index: 375299 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 2.1325. Min Range: -2.1325

Max Act: 1.6869. Min Act: -0.0000

Data Index: 934294 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 2.1325. Min Range: -2.1325

Max Act: 1.6044. Min Act: -0.0000

Data Index: 1148372 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 2.1325. Min Range: -2.1325

Max Act: 1.4455. Min Act: -0.0000

Data Index: 905250 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 2.1325. Min Range: -2.1325

Max Act: 1.3900. Min Act: -0.0000

Data Index: 242756 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 2.1325. Min Range: -2.1325

Max Act: 1.3789. Min Act: -0.0000

Data Index: 1170046 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 2.1325. Min Range: -2.1325

Max Act: 1.3045. Min Act: -0.0000

Data Index: 470085 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 2.1325. Min Range: -2.1325

Max Act: 1.3511. Min Act: -0.0000

Data Index: 581873 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 2.1325. Min Range: -2.1325

Max Act: 1.3397. Min Act: -0.0000

Data Index: 988162 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 2.1325. Min Range: -2.1325

Max Act: 1.3187. Min Act: -0.0000

Data Index: 1292950 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 2.1325. Min Range: -2.1325

Max Act: 1.3504. Min Act: -0.0000

Data Index: 900561 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 2.1325. Min Range: -2.1325

Max Act: 1.3918. Min Act: -0.0000

Data Index: 677849 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 2.1325. Min Range: -2.1325

Max Act: 1.2928. Min Act: -0.0000

Data Index: 938616 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 2.1325. Min Range: -2.1325

Max Act: 1.2839. Min Act: -0.0000

Data Index: 1322519 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 2.1325. Min Range: -2.1325

Max Act: 1.2725. Min Act: -0.0000

Data Index: 215138 (C4 (Web Text))

Max Activating Token Index: 415

Text #18

Max Range: 2.1325. Min Range: -2.1325

Max Act: 1.4249. Min Act: -0.0000

Data Index: 1036233 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 2.1325. Min Range: -2.1325

Max Act: 1.1883. Min Act: -0.0000

Data Index: 413645 (C4 (Web Text))

Max Activating Token Index: 18