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

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

Neuron 4363 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8651. Min Range: -0.8651

Max Act: 0.8651. Min Act: -0.0003

Data Index: 267385 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 0.8651. Min Range: -0.8651

Max Act: 0.7721. Min Act: -0.0003

Data Index: 193217 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 0.8651. Min Range: -0.8651

Max Act: 0.7902. Min Act: -0.0002

Data Index: 379800 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 0.8651. Min Range: -0.8651

Max Act: 0.7637. Min Act: -0.0002

Data Index: 842995 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 0.8651. Min Range: -0.8651

Max Act: 0.7576. Min Act: -0.0003

Data Index: 299624 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 0.8651. Min Range: -0.8651

Max Act: 0.7410. Min Act: -0.0003

Data Index: 71351 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 0.8651. Min Range: -0.8651

Max Act: 0.7538. Min Act: -0.0002

Data Index: 1165676 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 0.8651. Min Range: -0.8651

Max Act: 0.6950. Min Act: -0.0002

Data Index: 1325732 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 0.8651. Min Range: -0.8651

Max Act: 0.6906. Min Act: -0.0003

Data Index: 1270184 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 0.8651. Min Range: -0.8651

Max Act: 0.6900. Min Act: -0.0003

Data Index: 236375 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 0.8651. Min Range: -0.8651

Max Act: 0.7092. Min Act: -0.0003

Data Index: 80388 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 0.8651. Min Range: -0.8651

Max Act: 0.6545. Min Act: -0.0003

Data Index: 1267973 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 0.8651. Min Range: -0.8651

Max Act: 0.6872. Min Act: -0.0003

Data Index: 900371 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 0.8651. Min Range: -0.8651

Max Act: 0.6815. Min Act: -0.0003

Data Index: 666851 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 0.8651. Min Range: -0.8651

Max Act: 0.6572. Min Act: -0.0002

Data Index: 348288 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 0.8651. Min Range: -0.8651

Max Act: 0.6590. Min Act: -0.0003

Data Index: 130578 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 0.8651. Min Range: -0.8651

Max Act: 0.6678. Min Act: -0.0002

Data Index: 374825 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 0.8651. Min Range: -0.8651

Max Act: 0.6257. Min Act: -0.0002

Data Index: 159105 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 0.8651. Min Range: -0.8651

Max Act: 0.6270. Min Act: -0.0003

Data Index: 422381 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 0.8651. Min Range: -0.8651

Max Act: 0.6640. Min Act: -0.0003

Data Index: 586922 (C4 (Web Text))

Max Activating Token Index: 541