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

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

Neuron 1802 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.7586. Min Act: -0.0000

Data Index: 420709 (C4 (Web Text))

Max Activating Token Index: 226

Text #1

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.7639. Min Act: -0.0001

Data Index: 134446 (C4 (Web Text))

Max Activating Token Index: 705

Text #2

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.6246. Min Act: -0.0000

Data Index: 1155817 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.7159. Min Act: -0.0001

Data Index: 73903 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.6453. Min Act: -0.0001

Data Index: 1172200 (C4 (Web Text))

Max Activating Token Index: 1022

Text #5

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.6298. Min Act: -0.0000

Data Index: 1336850 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.6551. Min Act: -0.0000

Data Index: 703774 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.6520. Min Act: -0.0000

Data Index: 42516 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.5878. Min Act: -0.0001

Data Index: 935046 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.5920. Min Act: -0.0000

Data Index: 159435 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.5621. Min Act: -0.0000

Data Index: 909244 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.5626. Min Act: -0.0000

Data Index: 810515 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.5530. Min Act: -0.0000

Data Index: 145928 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.6062. Min Act: -0.0000

Data Index: 232508 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.5538. Min Act: -0.0000

Data Index: 1165484 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.5867. Min Act: -0.0001

Data Index: 533907 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.5590. Min Act: -0.0000

Data Index: 639177 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.5584. Min Act: -0.0000

Data Index: 1123065 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.5276. Min Act: -0.0000

Data Index: 504212 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 0.7639. Min Range: -0.7639

Max Act: 0.5282. Min Act: -0.0000

Data Index: 101991 (C4 (Web Text))

Max Activating Token Index: 153