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

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

Neuron 1697 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0624. Min Act: -0.0003

Data Index: 860537 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0557. Min Act: -0.0003

Data Index: 356998 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0553. Min Act: -0.0003

Data Index: 1247107 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0547. Min Act: -0.0003

Data Index: 394729 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0495. Min Act: -0.0003

Data Index: 1093192 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0569. Min Act: -0.0003

Data Index: 1082479 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0515. Min Act: -0.0003

Data Index: 355127 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0530. Min Act: -0.0003

Data Index: 1098785 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0520. Min Act: -0.0003

Data Index: 1264761 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0534. Min Act: -0.0003

Data Index: 1154164 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0509. Min Act: -0.0003

Data Index: 819506 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0500. Min Act: -0.0003

Data Index: 1234063 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0472. Min Act: -0.0003

Data Index: 791614 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0485. Min Act: -0.0003

Data Index: 809603 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0493. Min Act: -0.0003

Data Index: 1202750 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0514. Min Act: -0.0003

Data Index: 784842 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0525. Min Act: -0.0003

Data Index: 1271588 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0472. Min Act: -0.0003

Data Index: 295595 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0488. Min Act: -0.0003

Data Index: 206121 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0517. Min Act: -0.0003

Data Index: 249661 (C4 (Web Text))

Max Activating Token Index: 435