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

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

Neuron 2926 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: 1.3426. Min Range: -1.3426

Max Act: 1.2968. Min Act: -0.0000

Data Index: 908696 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 1.3426. Min Range: -1.3426

Max Act: 1.3068. Min Act: -0.0000

Data Index: 506083 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 1.3426. Min Range: -1.3426

Max Act: 1.3426. Min Act: -0.0000

Data Index: 676861 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 1.3426. Min Range: -1.3426

Max Act: 1.2631. Min Act: -0.0000

Data Index: 1327098 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 1.3426. Min Range: -1.3426

Max Act: 1.2367. Min Act: -0.0000

Data Index: 1273934 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 1.3426. Min Range: -1.3426

Max Act: 1.1232. Min Act: -0.0000

Data Index: 313612 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 1.3426. Min Range: -1.3426

Max Act: 1.1110. Min Act: -0.0000

Data Index: 494529 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 1.3426. Min Range: -1.3426

Max Act: 1.1084. Min Act: -0.0000

Data Index: 1245817 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 1.3426. Min Range: -1.3426

Max Act: 1.1578. Min Act: -0.0000

Data Index: 216115 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 1.3426. Min Range: -1.3426

Max Act: 1.0817. Min Act: -0.0000

Data Index: 24151 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 1.3426. Min Range: -1.3426

Max Act: 1.0816. Min Act: -0.0000

Data Index: 92170 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 1.3426. Min Range: -1.3426

Max Act: 1.0841. Min Act: -0.0000

Data Index: 827417 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 1.3426. Min Range: -1.3426

Max Act: 1.0174. Min Act: -0.0000

Data Index: 990721 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 1.3426. Min Range: -1.3426

Max Act: 1.1463. Min Act: -0.0000

Data Index: 837366 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 1.3426. Min Range: -1.3426

Max Act: 1.0670. Min Act: -0.0000

Data Index: 1098944 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 1.3426. Min Range: -1.3426

Max Act: 1.1297. Min Act: -0.0000

Data Index: 1108837 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 1.3426. Min Range: -1.3426

Max Act: 0.9992. Min Act: -0.0000

Data Index: 486917 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 1.3426. Min Range: -1.3426

Max Act: 1.1195. Min Act: -0.0000

Data Index: 619368 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 1.3426. Min Range: -1.3426

Max Act: 0.9920. Min Act: -0.0000

Data Index: 1119400 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 1.3426. Min Range: -1.3426

Max Act: 1.0428. Min Act: -0.0000

Data Index: 86739 (C4 (Web Text))

Max Activating Token Index: 47