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

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

Neuron 1246 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9247. Min Range: -1.9247

Max Act: 1.9247. Min Act: -0.0001

Data Index: 602225 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 1.9247. Min Range: -1.9247

Max Act: 1.8815. Min Act: -0.0001

Data Index: 423677 (C4 (Web Text))

Max Activating Token Index: 971

Text #2

Max Range: 1.9247. Min Range: -1.9247

Max Act: 1.5647. Min Act: -0.0001

Data Index: 700894 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 1.9247. Min Range: -1.9247

Max Act: 1.4363. Min Act: -0.0001

Data Index: 979698 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 1.9247. Min Range: -1.9247

Max Act: 1.6091. Min Act: -0.0001

Data Index: 1102224 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 1.9247. Min Range: -1.9247

Max Act: 1.5980. Min Act: -0.0000

Data Index: 917249 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 1.9247. Min Range: -1.9247

Max Act: 1.3087. Min Act: -0.0001

Data Index: 1058492 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 1.9247. Min Range: -1.9247

Max Act: 1.3400. Min Act: -0.0001

Data Index: 200543 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 1.9247. Min Range: -1.9247

Max Act: 1.2623. Min Act: -0.0001

Data Index: 67524 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 1.9247. Min Range: -1.9247

Max Act: 1.3952. Min Act: -0.0000

Data Index: 1131102 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 1.9247. Min Range: -1.9247

Max Act: 1.2389. Min Act: -0.0001

Data Index: 781707 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 1.9247. Min Range: -1.9247

Max Act: 1.3078. Min Act: -0.0000

Data Index: 628642 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 1.9247. Min Range: -1.9247

Max Act: 1.2058. Min Act: -0.0000

Data Index: 329899 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 1.9247. Min Range: -1.9247

Max Act: 1.2635. Min Act: -0.0001

Data Index: 707014 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 1.9247. Min Range: -1.9247

Max Act: 1.2094. Min Act: -0.0001

Data Index: 478209 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 1.9247. Min Range: -1.9247

Max Act: 1.2676. Min Act: -0.0001

Data Index: 318340 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 1.9247. Min Range: -1.9247

Max Act: 1.1932. Min Act: -0.0000

Data Index: 1219266 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 1.9247. Min Range: -1.9247

Max Act: 1.1936. Min Act: -0.0001

Data Index: 1103125 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 1.9247. Min Range: -1.9247

Max Act: 1.2203. Min Act: -0.0001

Data Index: 896939 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 1.9247. Min Range: -1.9247

Max Act: 1.2111. Min Act: -0.0001

Data Index: 323849 (C4 (Web Text))

Max Activating Token Index: 385