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

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

Neuron 2771 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: 1.6188. Min Range: -1.6188

Max Act: 1.6188. Min Act: -0.0000

Data Index: 615711 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.5992. Min Act: -0.0000

Data Index: 544893 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.5706. Min Act: -0.0000

Data Index: 184085 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.5237. Min Act: -0.0000

Data Index: 717101 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.5175. Min Act: -0.0000

Data Index: 1139365 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.4316. Min Act: -0.0000

Data Index: 1349377 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.4210. Min Act: -0.0000

Data Index: 344308 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.4949. Min Act: -0.0000

Data Index: 1042499 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.4402. Min Act: -0.0000

Data Index: 1201740 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.3900. Min Act: -0.0000

Data Index: 82004 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.4240. Min Act: -0.0000

Data Index: 1140844 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.4491. Min Act: -0.0000

Data Index: 1340477 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.3594. Min Act: -0.0000

Data Index: 105817 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.2874. Min Act: -0.0000

Data Index: 1005653 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.3651. Min Act: -0.0000

Data Index: 1250371 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.3222. Min Act: -0.0000

Data Index: 1066209 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.4729. Min Act: -0.0000

Data Index: 5171 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.3817. Min Act: -0.0000

Data Index: 420320 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.3279. Min Act: -0.0000

Data Index: 1333875 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.2775. Min Act: -0.0000

Data Index: 927991 (C4 (Web Text))

Max Activating Token Index: 361