Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3429 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.9089. Min Act: -0.0001

Data Index: 136266 (C4 (Web Text))

Max Activating Token Index: 843

Text #1

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.9002. Min Act: -0.0000

Data Index: 18492 (C4 (Web Text))

Max Activating Token Index: 859

Text #2

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.8320. Min Act: -0.0001

Data Index: 1203165 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.8524. Min Act: -0.0000

Data Index: 74033 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.8113. Min Act: -0.0000

Data Index: 70087 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.8170. Min Act: -0.0001

Data Index: 579255 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.8268. Min Act: -0.0000

Data Index: 965814 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.7757. Min Act: -0.0000

Data Index: 486862 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.7420. Min Act: -0.0001

Data Index: 53685 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.7996. Min Act: -0.0001

Data Index: 331464 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.7416. Min Act: -0.0000

Data Index: 1203565 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.6744. Min Act: -0.0001

Data Index: 571513 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.7599. Min Act: -0.0001

Data Index: 239104 (C4 (Web Text))

Max Activating Token Index: 762

Text #13

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.7201. Min Act: -0.0000

Data Index: 102674 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.7150. Min Act: -0.0000

Data Index: 1056004 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.7139. Min Act: -0.0000

Data Index: 188023 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.7359. Min Act: -0.0000

Data Index: 163339 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.6849. Min Act: -0.0000

Data Index: 1358258 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.7005. Min Act: -0.0001

Data Index: 822348 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.7040. Min Act: -0.0001

Data Index: 547183 (C4 (Web Text))

Max Activating Token Index: 1007