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

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

Neuron 4773 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8163. Min Range: -1.8163

Max Act: 1.8163. Min Act: -0.0000

Data Index: 226558 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 1.8163. Min Range: -1.8163

Max Act: 1.5195. Min Act: -0.0000

Data Index: 170480 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 1.8163. Min Range: -1.8163

Max Act: 1.2241. Min Act: -0.0000

Data Index: 263900 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 1.8163. Min Range: -1.8163

Max Act: 1.0756. Min Act: -0.0000

Data Index: 1226155 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 1.8163. Min Range: -1.8163

Max Act: 1.0475. Min Act: -0.0000

Data Index: 1262252 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 1.8163. Min Range: -1.8163

Max Act: 1.0612. Min Act: -0.0000

Data Index: 990610 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 1.8163. Min Range: -1.8163

Max Act: 0.9412. Min Act: -0.0000

Data Index: 421747 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 1.8163. Min Range: -1.8163

Max Act: 0.8353. Min Act: -0.0000

Data Index: 629539 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 1.8163. Min Range: -1.8163

Max Act: 0.9867. Min Act: -0.0000

Data Index: 1260787 (C4 (Web Text))

Max Activating Token Index: 732

Text #9

Max Range: 1.8163. Min Range: -1.8163

Max Act: 0.9972. Min Act: -0.0000

Data Index: 479384 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 1.8163. Min Range: -1.8163

Max Act: 0.8234. Min Act: -0.0000

Data Index: 917910 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 1.8163. Min Range: -1.8163

Max Act: 0.8303. Min Act: -0.0000

Data Index: 46828 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 1.8163. Min Range: -1.8163

Max Act: 0.9324. Min Act: -0.0000

Data Index: 927864 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 1.8163. Min Range: -1.8163

Max Act: 0.7793. Min Act: -0.0000

Data Index: 1437196 (Python Code)

Max Activating Token Index: 861

Text #14

Max Range: 1.8163. Min Range: -1.8163

Max Act: 0.8940. Min Act: -0.0000

Data Index: 198513 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 1.8163. Min Range: -1.8163

Max Act: 0.8425. Min Act: -0.0000

Data Index: 1303595 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 1.8163. Min Range: -1.8163

Max Act: 0.8744. Min Act: -0.0000

Data Index: 1051969 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 1.8163. Min Range: -1.8163

Max Act: 0.8638. Min Act: -0.0000

Data Index: 654160 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 1.8163. Min Range: -1.8163

Max Act: 0.7203. Min Act: -0.0000

Data Index: 1631512 (Python Code)

Max Activating Token Index: 746

Text #19

Max Range: 1.8163. Min Range: -1.8163

Max Act: 0.7806. Min Act: -0.0000

Data Index: 1349148 (C4 (Web Text))

Max Activating Token Index: 526