Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2938 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.3900. Min Act: 0.0001

Data Index: 1287020 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2956. Min Act: -0.0000

Data Index: 961952 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.3051. Min Act: -0.0000

Data Index: 92326 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2865. Min Act: -0.0000

Data Index: 1238936 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2839. Min Act: -0.0000

Data Index: 890260 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2822. Min Act: -0.0000

Data Index: 693100 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2764. Min Act: -0.0000

Data Index: 1217553 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2586. Min Act: 0.0000

Data Index: 841388 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2673. Min Act: -0.0000

Data Index: 510195 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2654. Min Act: -0.0000

Data Index: 308835 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2536. Min Act: -0.0000

Data Index: 59755 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2502. Min Act: -0.0000

Data Index: 660481 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2583. Min Act: -0.0000

Data Index: 1284018 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2534. Min Act: -0.0000

Data Index: 1048871 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2486. Min Act: -0.0000

Data Index: 1315581 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2419. Min Act: 0.0000

Data Index: 999878 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2440. Min Act: -0.0000

Data Index: 914414 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2441. Min Act: 0.0000

Data Index: 334409 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2363. Min Act: 0.0000

Data Index: 9877 (C4 (Web Text))

Max Activating Token Index: 457

Text #19

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2409. Min Act: -0.0000

Data Index: 1209405 (C4 (Web Text))

Max Activating Token Index: 601