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

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

Neuron 1085 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: 2.1353. Min Range: -2.1353

Max Act: 2.1353. Min Act: -0.0000

Data Index: 998189 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 2.1353. Min Range: -2.1353

Max Act: 1.8332. Min Act: -0.0000

Data Index: 675936 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 2.1353. Min Range: -2.1353

Max Act: 1.8381. Min Act: -0.0000

Data Index: 1122375 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 2.1353. Min Range: -2.1353

Max Act: 1.8302. Min Act: -0.0000

Data Index: 379222 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 2.1353. Min Range: -2.1353

Max Act: 1.7014. Min Act: -0.0000

Data Index: 237119 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 2.1353. Min Range: -2.1353

Max Act: 1.6667. Min Act: -0.0000

Data Index: 1343162 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 2.1353. Min Range: -2.1353

Max Act: 1.6440. Min Act: -0.0000

Data Index: 1269369 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 2.1353. Min Range: -2.1353

Max Act: 1.6392. Min Act: -0.0000

Data Index: 889885 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 2.1353. Min Range: -2.1353

Max Act: 1.6584. Min Act: -0.0000

Data Index: 1312047 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 2.1353. Min Range: -2.1353

Max Act: 1.6159. Min Act: -0.0000

Data Index: 21082 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 2.1353. Min Range: -2.1353

Max Act: 1.4884. Min Act: -0.0000

Data Index: 271078 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 2.1353. Min Range: -2.1353

Max Act: 1.4956. Min Act: -0.0000

Data Index: 258148 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 2.1353. Min Range: -2.1353

Max Act: 1.5537. Min Act: -0.0000

Data Index: 1142965 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 2.1353. Min Range: -2.1353

Max Act: 1.4375. Min Act: -0.0000

Data Index: 914216 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 2.1353. Min Range: -2.1353

Max Act: 1.5151. Min Act: -0.0000

Data Index: 709068 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 2.1353. Min Range: -2.1353

Max Act: 1.5681. Min Act: -0.0000

Data Index: 1173045 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 2.1353. Min Range: -2.1353

Max Act: 1.6194. Min Act: -0.0000

Data Index: 1258510 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 2.1353. Min Range: -2.1353

Max Act: 1.5208. Min Act: -0.0000

Data Index: 514167 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 2.1353. Min Range: -2.1353

Max Act: 1.5021. Min Act: -0.0000

Data Index: 880210 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 2.1353. Min Range: -2.1353

Max Act: 1.6110. Min Act: -0.0000

Data Index: 822896 (C4 (Web Text))

Max Activating Token Index: 687