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

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

Neuron 3450 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: 2.4767. Min Range: -2.4767

Max Act: 2.4505. Min Act: -0.0000

Data Index: 949730 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 2.4767. Min Range: -2.4767

Max Act: 2.3324. Min Act: -0.0000

Data Index: 1210069 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 2.4767. Min Range: -2.4767

Max Act: 2.2797. Min Act: -0.0000

Data Index: 1095861 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 2.4767. Min Range: -2.4767

Max Act: 2.4767. Min Act: -0.0000

Data Index: 990899 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 2.4767. Min Range: -2.4767

Max Act: 2.2029. Min Act: -0.0000

Data Index: 376610 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 2.4767. Min Range: -2.4767

Max Act: 2.2894. Min Act: -0.0000

Data Index: 1834 (C4 (Web Text))

Max Activating Token Index: 817

Text #6

Max Range: 2.4767. Min Range: -2.4767

Max Act: 2.1614. Min Act: -0.0000

Data Index: 182004 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 2.4767. Min Range: -2.4767

Max Act: 2.2599. Min Act: -0.0000

Data Index: 954052 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 2.4767. Min Range: -2.4767

Max Act: 2.1243. Min Act: -0.0000

Data Index: 334183 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 2.4767. Min Range: -2.4767

Max Act: 2.1170. Min Act: -0.0000

Data Index: 752273 (C4 (Web Text))

Max Activating Token Index: 589

Text #10

Max Range: 2.4767. Min Range: -2.4767

Max Act: 2.3400. Min Act: -0.0000

Data Index: 1335287 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 2.4767. Min Range: -2.4767

Max Act: 2.2035. Min Act: -0.0000

Data Index: 580322 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 2.4767. Min Range: -2.4767

Max Act: 2.2057. Min Act: -0.0000

Data Index: 1195412 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 2.4767. Min Range: -2.4767

Max Act: 2.1743. Min Act: -0.0000

Data Index: 313749 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 2.4767. Min Range: -2.4767

Max Act: 2.0457. Min Act: -0.0000

Data Index: 1284155 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 2.4767. Min Range: -2.4767

Max Act: 2.1560. Min Act: -0.0000

Data Index: 143914 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 2.4767. Min Range: -2.4767

Max Act: 2.2357. Min Act: -0.0000

Data Index: 752303 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 2.4767. Min Range: -2.4767

Max Act: 2.1303. Min Act: -0.0000

Data Index: 254436 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 2.4767. Min Range: -2.4767

Max Act: 2.0318. Min Act: -0.0000

Data Index: 1122717 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 2.4767. Min Range: -2.4767

Max Act: 1.9337. Min Act: -0.0000

Data Index: 306187 (C4 (Web Text))

Max Activating Token Index: 1003