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

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

Neuron 1191 in Layer 0

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: 0.0189. Min Range: -0.0189

Max Act: 0.0189. Min Act: -0.0001

Data Index: 773071 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0185. Min Act: -0.0001

Data Index: 1084826 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0186. Min Act: -0.0001

Data Index: 97832 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0185. Min Act: -0.0001

Data Index: 57792 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0187. Min Act: -0.0002

Data Index: 718314 (C4 (Web Text))

Max Activating Token Index: 271

Text #5

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0186. Min Act: -0.0001

Data Index: 1396950 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0186. Min Act: -0.0001

Data Index: 992229 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0184. Min Act: -0.0002

Data Index: 1595535 (Python Code)

Max Activating Token Index: 10

Text #8

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0183. Min Act: -0.0001

Data Index: 986895 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0185. Min Act: -0.0001

Data Index: 1412005 (Python Code)

Max Activating Token Index: 791

Text #10

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0180. Min Act: -0.0001

Data Index: 463510 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0178. Min Act: -0.0001

Data Index: 659768 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0178. Min Act: -0.0001

Data Index: 1170172 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0178. Min Act: -0.0001

Data Index: 723190 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0178. Min Act: -0.0001

Data Index: 101643 (C4 (Web Text))

Max Activating Token Index: 492

Text #15

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0176. Min Act: -0.0001

Data Index: 1273847 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0175. Min Act: -0.0001

Data Index: 1576528 (Python Code)

Max Activating Token Index: 159

Text #17

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0175. Min Act: -0.0001

Data Index: 148463 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0176. Min Act: -0.0001

Data Index: 1540051 (Python Code)

Max Activating Token Index: 689

Text #19

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0174. Min Act: -0.0001

Data Index: 1566259 (Python Code)

Max Activating Token Index: 946