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

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

Neuron 1869 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: 0.0681. Min Range: -0.0681

Max Act: 0.0681. Min Act: -0.0003

Data Index: 512210 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0673. Min Act: -0.0003

Data Index: 129255 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0657. Min Act: -0.0004

Data Index: 873402 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0658. Min Act: -0.0003

Data Index: 118019 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0665. Min Act: -0.0003

Data Index: 1139380 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0661. Min Act: -0.0003

Data Index: 14324 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0651. Min Act: -0.0003

Data Index: 1118258 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0666. Min Act: -0.0003

Data Index: 967608 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0631. Min Act: -0.0003

Data Index: 1085909 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0649. Min Act: -0.0003

Data Index: 592905 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1510275 (Python Code)

Max Activating Token Index: 799

Text #11

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0624. Min Act: -0.0003

Data Index: 715636 (C4 (Web Text))

Max Activating Token Index: 681

Text #12

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0632. Min Act: -0.0004

Data Index: 165426 (C4 (Web Text))

Max Activating Token Index: 630

Text #13

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0627. Min Act: -0.0004

Data Index: 495097 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0598. Min Act: -0.0003

Data Index: 254830 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0600. Min Act: -0.0003

Data Index: 392193 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0595. Min Act: -0.0003

Data Index: 145315 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0580. Min Act: -0.0003

Data Index: 1050695 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0597. Min Act: -0.0003

Data Index: 149169 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0591. Min Act: -0.0003

Data Index: 306039 (C4 (Web Text))

Max Activating Token Index: 909