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

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

Neuron 1644 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: 0.0670. Min Range: -0.0670

Max Act: 0.0670. Min Act: -0.0003

Data Index: 1166530 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0595. Min Act: -0.0003

Data Index: 848885 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0562. Min Act: -0.0003

Data Index: 714515 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0543. Min Act: -0.0003

Data Index: 1230170 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0509. Min Act: -0.0003

Data Index: 578809 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0488. Min Act: -0.0003

Data Index: 657302 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0491. Min Act: -0.0003

Data Index: 556427 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0508. Min Act: -0.0003

Data Index: 1266488 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0484. Min Act: -0.0003

Data Index: 99018 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0496. Min Act: -0.0003

Data Index: 367551 (C4 (Web Text))

Max Activating Token Index: 273

Text #10

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0468. Min Act: -0.0003

Data Index: 788001 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0488. Min Act: -0.0003

Data Index: 1116064 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0466. Min Act: -0.0003

Data Index: 740962 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0480. Min Act: -0.0003

Data Index: 735498 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0483. Min Act: -0.0003

Data Index: 1103485 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0467. Min Act: -0.0003

Data Index: 1026290 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0457. Min Act: -0.0003

Data Index: 104045 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0478. Min Act: -0.0003

Data Index: 226458 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0468. Min Act: -0.0003

Data Index: 1352774 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0455. Min Act: -0.0003

Data Index: 65243 (C4 (Web Text))

Max Activating Token Index: 704