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

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

Neuron 1284 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: 0.2968. Min Range: -0.2968

Max Act: 0.2968. Min Act: -0.0000

Data Index: 170519 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2558. Min Act: -0.0001

Data Index: 214345 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2615. Min Act: -0.0000

Data Index: 251992 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2587. Min Act: -0.0000

Data Index: 1018889 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2583. Min Act: -0.0000

Data Index: 974834 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2655. Min Act: -0.0001

Data Index: 886281 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2547. Min Act: -0.0000

Data Index: 1277696 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2392. Min Act: -0.0001

Data Index: 487727 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2374. Min Act: -0.0000

Data Index: 966185 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2388. Min Act: -0.0000

Data Index: 663548 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2269. Min Act: -0.0000

Data Index: 663239 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2512. Min Act: -0.0001

Data Index: 1078453 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2278. Min Act: -0.0001

Data Index: 1421587 (Python Code)

Max Activating Token Index: 590

Text #13

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2345. Min Act: -0.0000

Data Index: 904707 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2321. Min Act: -0.0000

Data Index: 481538 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2482. Min Act: -0.0000

Data Index: 918462 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2093. Min Act: -0.0000

Data Index: 1328148 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2398. Min Act: -0.0000

Data Index: 1340945 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2072. Min Act: -0.0000

Data Index: 280035 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2015. Min Act: -0.0000

Data Index: 387106 (C4 (Web Text))

Max Activating Token Index: 690