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

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

Neuron 3230 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1194. Min Range: -3.1194

Max Act: 3.1194. Min Act: -0.0000

Data Index: 1129552 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 3.1194. Min Range: -3.1194

Max Act: 2.9016. Min Act: -0.0000

Data Index: 468166 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 3.1194. Min Range: -3.1194

Max Act: 2.3717. Min Act: -0.0000

Data Index: 726829 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 3.1194. Min Range: -3.1194

Max Act: 2.5910. Min Act: -0.0000

Data Index: 932399 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 3.1194. Min Range: -3.1194

Max Act: 2.4070. Min Act: -0.0000

Data Index: 1195648 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 3.1194. Min Range: -3.1194

Max Act: 2.0187. Min Act: -0.0000

Data Index: 180821 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 3.1194. Min Range: -3.1194

Max Act: 2.2172. Min Act: -0.0000

Data Index: 911060 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 3.1194. Min Range: -3.1194

Max Act: 2.2146. Min Act: -0.0000

Data Index: 739954 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 3.1194. Min Range: -3.1194

Max Act: 2.1407. Min Act: -0.0000

Data Index: 1091537 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 3.1194. Min Range: -3.1194

Max Act: 2.0416. Min Act: -0.0000

Data Index: 498785 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 3.1194. Min Range: -3.1194

Max Act: 2.2545. Min Act: -0.0000

Data Index: 401186 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 3.1194. Min Range: -3.1194

Max Act: 2.0991. Min Act: -0.0000

Data Index: 1181709 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 3.1194. Min Range: -3.1194

Max Act: 1.8554. Min Act: -0.0000

Data Index: 1089097 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 3.1194. Min Range: -3.1194

Max Act: 2.2211. Min Act: -0.0000

Data Index: 1095529 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 3.1194. Min Range: -3.1194

Max Act: 2.6303. Min Act: -0.0000

Data Index: 1173835 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 3.1194. Min Range: -3.1194

Max Act: 2.2225. Min Act: -0.0000

Data Index: 652589 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 3.1194. Min Range: -3.1194

Max Act: 2.1133. Min Act: -0.0000

Data Index: 1280486 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 3.1194. Min Range: -3.1194

Max Act: 1.9364. Min Act: -0.0000

Data Index: 963330 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 3.1194. Min Range: -3.1194

Max Act: 2.0747. Min Act: -0.0000

Data Index: 31247 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 3.1194. Min Range: -3.1194

Max Act: 1.9147. Min Act: -0.0000

Data Index: 925974 (C4 (Web Text))

Max Activating Token Index: 278