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

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

Neuron 1230 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: 1.8408. Min Range: -1.8408

Max Act: 1.8408. Min Act: -0.0000

Data Index: 449094 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 1.8408. Min Range: -1.8408

Max Act: 1.6676. Min Act: -0.0000

Data Index: 819742 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 1.8408. Min Range: -1.8408

Max Act: 1.4427. Min Act: -0.0000

Data Index: 1058250 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 1.8408. Min Range: -1.8408

Max Act: 1.4205. Min Act: -0.0000

Data Index: 671825 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 1.8408. Min Range: -1.8408

Max Act: 1.3694. Min Act: -0.0000

Data Index: 1084948 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 1.8408. Min Range: -1.8408

Max Act: 1.4424. Min Act: -0.0000

Data Index: 257576 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 1.8408. Min Range: -1.8408

Max Act: 1.3449. Min Act: -0.0000

Data Index: 1205864 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 1.8408. Min Range: -1.8408

Max Act: 1.4063. Min Act: -0.0000

Data Index: 1134929 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 1.8408. Min Range: -1.8408

Max Act: 1.3229. Min Act: -0.0000

Data Index: 509824 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 1.8408. Min Range: -1.8408

Max Act: 1.4007. Min Act: -0.0000

Data Index: 649642 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 1.8408. Min Range: -1.8408

Max Act: 1.4336. Min Act: -0.0000

Data Index: 1343293 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 1.8408. Min Range: -1.8408

Max Act: 1.2366. Min Act: -0.0000

Data Index: 615440 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 1.8408. Min Range: -1.8408

Max Act: 1.3586. Min Act: -0.0000

Data Index: 550862 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 1.8408. Min Range: -1.8408

Max Act: 1.2809. Min Act: -0.0000

Data Index: 1101935 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 1.8408. Min Range: -1.8408

Max Act: 1.2483. Min Act: -0.0000

Data Index: 58281 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 1.8408. Min Range: -1.8408

Max Act: 1.1688. Min Act: -0.0000

Data Index: 188172 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 1.8408. Min Range: -1.8408

Max Act: 1.3141. Min Act: -0.0000

Data Index: 787961 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 1.8408. Min Range: -1.8408

Max Act: 1.1555. Min Act: -0.0000

Data Index: 423471 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 1.8408. Min Range: -1.8408

Max Act: 1.2255. Min Act: -0.0000

Data Index: 71400 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 1.8408. Min Range: -1.8408

Max Act: 1.1930. Min Act: -0.0000

Data Index: 447854 (C4 (Web Text))

Max Activating Token Index: 35