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

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

Neuron 4636 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2212. Min Range: -1.2212

Max Act: 1.2212. Min Act: -0.0000

Data Index: 332356 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 1.2212. Min Range: -1.2212

Max Act: 1.1326. Min Act: -0.0000

Data Index: 292040 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 1.2212. Min Range: -1.2212

Max Act: 1.0898. Min Act: -0.0000

Data Index: 787648 (C4 (Web Text))

Max Activating Token Index: 329

Text #3

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.8772. Min Act: -0.0000

Data Index: 25125 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.9006. Min Act: -0.0000

Data Index: 345047 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.8185. Min Act: -0.0000

Data Index: 404039 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.7794. Min Act: -0.0000

Data Index: 1260591 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.8157. Min Act: -0.0000

Data Index: 831057 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.6946. Min Act: -0.0000

Data Index: 683152 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.7082. Min Act: -0.0000

Data Index: 845930 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.7367. Min Act: -0.0000

Data Index: 1087478 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.7729. Min Act: -0.0000

Data Index: 390498 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.7175. Min Act: -0.0000

Data Index: 171500 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.6666. Min Act: -0.0000

Data Index: 107943 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.7157. Min Act: -0.0000

Data Index: 429015 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.6771. Min Act: -0.0000

Data Index: 663231 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.6946. Min Act: -0.0000

Data Index: 590261 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.6836. Min Act: -0.0000

Data Index: 1225904 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.6908. Min Act: -0.0000

Data Index: 913389 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.6875. Min Act: -0.0000

Data Index: 1164538 (C4 (Web Text))

Max Activating Token Index: 373