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

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

Neuron 3812 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: 0.0697. Min Range: -0.0697

Max Act: 0.0697. Min Act: -0.0003

Data Index: 1566856 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0624. Min Act: -0.0003

Data Index: 780596 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0622. Min Act: -0.0003

Data Index: 689155 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0579. Min Act: -0.0003

Data Index: 1167322 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0606. Min Act: -0.0003

Data Index: 1133115 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0608. Min Act: -0.0003

Data Index: 1519042 (Python Code)

Max Activating Token Index: 383

Text #6

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0644. Min Act: -0.0003

Data Index: 339 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0578. Min Act: -0.0003

Data Index: 1342453 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0537. Min Act: -0.0003

Data Index: 85187 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0550. Min Act: -0.0003

Data Index: 967143 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0526. Min Act: -0.0003

Data Index: 824240 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0456. Min Act: -0.0003

Data Index: 1408570 (Python Code)

Max Activating Token Index: 694

Text #12

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0535. Min Act: -0.0003

Data Index: 443080 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0576. Min Act: -0.0003

Data Index: 511226 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0531. Min Act: -0.0003

Data Index: 386707 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0555. Min Act: -0.0003

Data Index: 182911 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0547. Min Act: -0.0003

Data Index: 1237599 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0567. Min Act: -0.0003

Data Index: 330713 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0562. Min Act: -0.0003

Data Index: 584386 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0543. Min Act: -0.0003

Data Index: 345427 (C4 (Web Text))

Max Activating Token Index: 264