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

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

Neuron 628 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.9172. Min Act: -0.0000

Data Index: 1350333 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.9339. Min Act: -0.0000

Data Index: 992660 (C4 (Web Text))

Max Activating Token Index: 522

Text #2

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.8632. Min Act: -0.0000

Data Index: 892162 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.8032. Min Act: -0.0001

Data Index: 364474 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.8687. Min Act: -0.0000

Data Index: 1040444 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.8119. Min Act: -0.0000

Data Index: 1243491 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.8054. Min Act: -0.0001

Data Index: 443197 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.8499. Min Act: -0.0001

Data Index: 1121234 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.8241. Min Act: -0.0000

Data Index: 649828 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.8316. Min Act: -0.0001

Data Index: 515704 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.8432. Min Act: -0.0000

Data Index: 666007 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.7712. Min Act: -0.0001

Data Index: 1247118 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.7907. Min Act: -0.0000

Data Index: 647561 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.7440. Min Act: -0.0001

Data Index: 1283074 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6944. Min Act: -0.0000

Data Index: 1058459 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.7999. Min Act: -0.0000

Data Index: 471870 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.7765. Min Act: -0.0000

Data Index: 750630 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.7528. Min Act: -0.0000

Data Index: 447231 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.7666. Min Act: -0.0001

Data Index: 115562 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6751. Min Act: -0.0000

Data Index: 493097 (C4 (Web Text))

Max Activating Token Index: 369