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

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

Neuron 3779 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.3065. Min Act: -0.0000

Data Index: 811507 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2849. Min Act: -0.0000

Data Index: 820243 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2790. Min Act: -0.0000

Data Index: 752341 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2606. Min Act: -0.0000

Data Index: 260835 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2494. Min Act: -0.0000

Data Index: 1083651 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2552. Min Act: -0.0000

Data Index: 1130758 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2566. Min Act: -0.0000

Data Index: 553260 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2433. Min Act: -0.0000

Data Index: 889444 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2436. Min Act: -0.0000

Data Index: 1280668 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2331. Min Act: -0.0000

Data Index: 724064 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2335. Min Act: -0.0000

Data Index: 1110938 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2253. Min Act: -0.0000

Data Index: 365070 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2241. Min Act: -0.0000

Data Index: 1188099 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2183. Min Act: -0.0000

Data Index: 873176 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2076. Min Act: -0.0000

Data Index: 1353948 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2048. Min Act: -0.0000

Data Index: 216343 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2015. Min Act: -0.0000

Data Index: 494076 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2161. Min Act: -0.0000

Data Index: 184544 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2244. Min Act: -0.0000

Data Index: 165806 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2003. Min Act: -0.0000

Data Index: 964908 (C4 (Web Text))

Max Activating Token Index: 47