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

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

Neuron 493 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8964. Min Range: -0.8964

Max Act: 0.8929. Min Act: -0.0000

Data Index: 423026 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 0.8964. Min Range: -0.8964

Max Act: 0.8676. Min Act: -0.0000

Data Index: 812263 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 0.8964. Min Range: -0.8964

Max Act: 0.8964. Min Act: -0.0000

Data Index: 710410 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.8964. Min Range: -0.8964

Max Act: 0.7731. Min Act: -0.0000

Data Index: 322870 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 0.8964. Min Range: -0.8964

Max Act: 0.7865. Min Act: -0.0000

Data Index: 229109 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 0.8964. Min Range: -0.8964

Max Act: 0.7683. Min Act: -0.0000

Data Index: 166802 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 0.8964. Min Range: -0.8964

Max Act: 0.7648. Min Act: -0.0000

Data Index: 1348425 (C4 (Web Text))

Max Activating Token Index: 604

Text #7

Max Range: 0.8964. Min Range: -0.8964

Max Act: 0.7216. Min Act: -0.0000

Data Index: 1243430 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 0.8964. Min Range: -0.8964

Max Act: 0.8119. Min Act: 0.0000

Data Index: 1656012 (Python Code)

Max Activating Token Index: 97

Text #9

Max Range: 0.8964. Min Range: -0.8964

Max Act: 0.7290. Min Act: -0.0000

Data Index: 150187 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 0.8964. Min Range: -0.8964

Max Act: 0.6864. Min Act: 0.0000

Data Index: 264130 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 0.8964. Min Range: -0.8964

Max Act: 0.6740. Min Act: -0.0000

Data Index: 215869 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 0.8964. Min Range: -0.8964

Max Act: 0.7166. Min Act: -0.0000

Data Index: 1346907 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 0.8964. Min Range: -0.8964

Max Act: 0.7029. Min Act: -0.0000

Data Index: 1327487 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 0.8964. Min Range: -0.8964

Max Act: 0.7029. Min Act: -0.0000

Data Index: 622775 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 0.8964. Min Range: -0.8964

Max Act: 0.6975. Min Act: -0.0000

Data Index: 68410 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 0.8964. Min Range: -0.8964

Max Act: 0.6492. Min Act: 0.0001

Data Index: 1193508 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 0.8964. Min Range: -0.8964

Max Act: 0.6873. Min Act: -0.0000

Data Index: 618440 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 0.8964. Min Range: -0.8964

Max Act: 0.6566. Min Act: -0.0000

Data Index: 1234247 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 0.8964. Min Range: -0.8964

Max Act: 0.6908. Min Act: -0.0000

Data Index: 646166 (C4 (Web Text))

Max Activating Token Index: 552