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

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

Neuron 4002 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1286. Min Range: -1.1286

Max Act: 1.1144. Min Act: -0.0001

Data Index: 530939 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 1.1286. Min Range: -1.1286

Max Act: 1.1286. Min Act: -0.0001

Data Index: 1001684 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 1.1286. Min Range: -1.1286

Max Act: 1.0953. Min Act: -0.0001

Data Index: 407005 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 1.1286. Min Range: -1.1286

Max Act: 1.0681. Min Act: -0.0001

Data Index: 565073 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 1.1286. Min Range: -1.1286

Max Act: 1.0088. Min Act: -0.0001

Data Index: 240999 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.9604. Min Act: -0.0001

Data Index: 278577 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 1.1286. Min Range: -1.1286

Max Act: 1.0022. Min Act: -0.0001

Data Index: 984112 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.9173. Min Act: -0.0001

Data Index: 308642 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.9883. Min Act: -0.0001

Data Index: 1287730 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 1.1286. Min Range: -1.1286

Max Act: 1.0849. Min Act: -0.0001

Data Index: 50716 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.9880. Min Act: -0.0001

Data Index: 596194 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.7513. Min Act: -0.0001

Data Index: 1051499 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.8946. Min Act: -0.0001

Data Index: 58298 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.8562. Min Act: -0.0001

Data Index: 210863 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.8821. Min Act: -0.0001

Data Index: 385714 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.8856. Min Act: -0.0001

Data Index: 825494 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.8733. Min Act: -0.0001

Data Index: 720539 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.8921. Min Act: -0.0001

Data Index: 844627 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.8559. Min Act: -0.0001

Data Index: 571764 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.8081. Min Act: -0.0001

Data Index: 110349 (C4 (Web Text))

Max Activating Token Index: 600