Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1438 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0677. Min Act: -0.0003

Data Index: 1238632 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0659. Min Act: -0.0003

Data Index: 1138211 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0620. Min Act: -0.0003

Data Index: 1286480 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0600. Min Act: -0.0003

Data Index: 63363 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0575. Min Act: -0.0003

Data Index: 575412 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0584. Min Act: -0.0003

Data Index: 1191304 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0560. Min Act: -0.0004

Data Index: 67069 (C4 (Web Text))

Max Activating Token Index: 601

Text #7

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0569. Min Act: -0.0003

Data Index: 1335211 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0565. Min Act: -0.0003

Data Index: 1013392 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0553. Min Act: -0.0003

Data Index: 690063 (C4 (Web Text))

Max Activating Token Index: 768

Text #10

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0560. Min Act: -0.0004

Data Index: 1001969 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0557. Min Act: -0.0003

Data Index: 987619 (C4 (Web Text))

Max Activating Token Index: 389

Text #12

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0542. Min Act: -0.0003

Data Index: 1345209 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0543. Min Act: -0.0003

Data Index: 726095 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0540. Min Act: -0.0003

Data Index: 219011 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0539. Min Act: -0.0003

Data Index: 1204125 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0536. Min Act: -0.0003

Data Index: 63078 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0537. Min Act: -0.0003

Data Index: 823127 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0542. Min Act: -0.0003

Data Index: 478023 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0557. Min Act: -0.0003

Data Index: 1106967 (C4 (Web Text))

Max Activating Token Index: 849