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

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

Neuron 4826 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4025. Min Range: -2.4025

Max Act: 2.4025. Min Act: -0.0000

Data Index: 650525 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 2.4025. Min Range: -2.4025

Max Act: 1.8367. Min Act: -0.0000

Data Index: 32445 (C4 (Web Text))

Max Activating Token Index: 949

Text #2

Max Range: 2.4025. Min Range: -2.4025

Max Act: 1.6430. Min Act: -0.0000

Data Index: 562090 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 2.4025. Min Range: -2.4025

Max Act: 1.5043. Min Act: -0.0000

Data Index: 662375 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 2.4025. Min Range: -2.4025

Max Act: 1.5278. Min Act: -0.0000

Data Index: 1203487 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 2.4025. Min Range: -2.4025

Max Act: 1.4495. Min Act: -0.0000

Data Index: 1601499 (Python Code)

Max Activating Token Index: 37

Text #6

Max Range: 2.4025. Min Range: -2.4025

Max Act: 1.3408. Min Act: -0.0000

Data Index: 1540698 (Python Code)

Max Activating Token Index: 966

Text #7

Max Range: 2.4025. Min Range: -2.4025

Max Act: 1.3481. Min Act: -0.0000

Data Index: 1551354 (Python Code)

Max Activating Token Index: 692

Text #8

Max Range: 2.4025. Min Range: -2.4025

Max Act: 1.2985. Min Act: -0.0000

Data Index: 1427584 (Python Code)

Max Activating Token Index: 126

Text #9

Max Range: 2.4025. Min Range: -2.4025

Max Act: 1.3148. Min Act: -0.0000

Data Index: 476326 (C4 (Web Text))

Max Activating Token Index: 768

Text #10

Max Range: 2.4025. Min Range: -2.4025

Max Act: 1.3584. Min Act: -0.0000

Data Index: 1150237 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 2.4025. Min Range: -2.4025

Max Act: 1.1626. Min Act: -0.0000

Data Index: 565238 (C4 (Web Text))

Max Activating Token Index: 389

Text #12

Max Range: 2.4025. Min Range: -2.4025

Max Act: 1.2347. Min Act: -0.0000

Data Index: 1360622 (Python Code)

Max Activating Token Index: 322

Text #13

Max Range: 2.4025. Min Range: -2.4025

Max Act: 1.1921. Min Act: -0.0000

Data Index: 1180206 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 2.4025. Min Range: -2.4025

Max Act: 1.1892. Min Act: -0.0000

Data Index: 1441406 (Python Code)

Max Activating Token Index: 196

Text #15

Max Range: 2.4025. Min Range: -2.4025

Max Act: 1.0946. Min Act: -0.0000

Data Index: 1566202 (Python Code)

Max Activating Token Index: 822

Text #16

Max Range: 2.4025. Min Range: -2.4025

Max Act: 0.9936. Min Act: -0.0000

Data Index: 1034774 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 2.4025. Min Range: -2.4025

Max Act: 0.9869. Min Act: -0.0000

Data Index: 97840 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 2.4025. Min Range: -2.4025

Max Act: 1.1251. Min Act: -0.0000

Data Index: 1576140 (Python Code)

Max Activating Token Index: 752

Text #19

Max Range: 2.4025. Min Range: -2.4025

Max Act: 1.1289. Min Act: -0.0000

Data Index: 1586557 (Python Code)

Max Activating Token Index: 939