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

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

Neuron 4927 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.1103. Min Range: -1.1103

Max Act: 1.1103. Min Act: -0.0002

Data Index: 1271155 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 1.1103. Min Range: -1.1103

Max Act: 0.9771. Min Act: -0.0002

Data Index: 483445 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 1.1103. Min Range: -1.1103

Max Act: 0.8986. Min Act: -0.0002

Data Index: 66918 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 1.1103. Min Range: -1.1103

Max Act: 0.9041. Min Act: -0.0002

Data Index: 411788 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 1.1103. Min Range: -1.1103

Max Act: 0.8765. Min Act: -0.0002

Data Index: 955262 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 1.1103. Min Range: -1.1103

Max Act: 0.8876. Min Act: -0.0003

Data Index: 634256 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 1.1103. Min Range: -1.1103

Max Act: 0.8672. Min Act: -0.0002

Data Index: 379577 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 1.1103. Min Range: -1.1103

Max Act: 0.8505. Min Act: -0.0002

Data Index: 384146 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 1.1103. Min Range: -1.1103

Max Act: 0.8221. Min Act: -0.0002

Data Index: 1240872 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 1.1103. Min Range: -1.1103

Max Act: 0.8505. Min Act: -0.0002

Data Index: 118801 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 1.1103. Min Range: -1.1103

Max Act: 0.8460. Min Act: -0.0003

Data Index: 356317 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 1.1103. Min Range: -1.1103

Max Act: 0.8323. Min Act: -0.0002

Data Index: 1342814 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 1.1103. Min Range: -1.1103

Max Act: 0.8070. Min Act: -0.0002

Data Index: 331170 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 1.1103. Min Range: -1.1103

Max Act: 0.8296. Min Act: -0.0002

Data Index: 164172 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 1.1103. Min Range: -1.1103

Max Act: 0.8370. Min Act: -0.0003

Data Index: 639258 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 1.1103. Min Range: -1.1103

Max Act: 0.8165. Min Act: -0.0002

Data Index: 281193 (C4 (Web Text))

Max Activating Token Index: 339

Text #16

Max Range: 1.1103. Min Range: -1.1103

Max Act: 0.8212. Min Act: -0.0002

Data Index: 477790 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 1.1103. Min Range: -1.1103

Max Act: 0.8263. Min Act: -0.0002

Data Index: 150080 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 1.1103. Min Range: -1.1103

Max Act: 0.7870. Min Act: -0.0002

Data Index: 571464 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 1.1103. Min Range: -1.1103

Max Act: 0.7954. Min Act: -0.0002

Data Index: 871155 (C4 (Web Text))

Max Activating Token Index: 174