Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5118 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.9494. Min Act: -0.0000

Data Index: 194808 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.8377. Min Act: -0.0000

Data Index: 1262887 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.7864. Min Act: -0.0000

Data Index: 972572 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.7729. Min Act: -0.0000

Data Index: 57772 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.8104. Min Act: -0.0000

Data Index: 450558 (C4 (Web Text))

Max Activating Token Index: 412

Text #5

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.8117. Min Act: -0.0000

Data Index: 550438 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.7983. Min Act: -0.0000

Data Index: 407307 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.7079. Min Act: -0.0000

Data Index: 462176 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.7750. Min Act: -0.0000

Data Index: 963695 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.8303. Min Act: -0.0000

Data Index: 46573 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.7660. Min Act: -0.0000

Data Index: 1245055 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.7694. Min Act: -0.0000

Data Index: 1062288 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.6854. Min Act: -0.0000

Data Index: 86811 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.7248. Min Act: -0.0000

Data Index: 1187823 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.7221. Min Act: -0.0000

Data Index: 252429 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.7155. Min Act: -0.0000

Data Index: 846413 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.6994. Min Act: -0.0000

Data Index: 1144687 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.6998. Min Act: -0.0000

Data Index: 1265479 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.6898. Min Act: -0.0000

Data Index: 230888 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.6593. Min Act: -0.0000

Data Index: 727153 (C4 (Web Text))

Max Activating Token Index: 702