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

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

Neuron 755 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2345. Min Range: -4.2345

Max Act: 4.2345. Min Act: -0.0000

Data Index: 1047477 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 4.2345. Min Range: -4.2345

Max Act: 3.5276. Min Act: -0.0000

Data Index: 452605 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 4.2345. Min Range: -4.2345

Max Act: 3.1188. Min Act: -0.0000

Data Index: 205025 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 4.2345. Min Range: -4.2345

Max Act: 2.8088. Min Act: -0.0000

Data Index: 1282476 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 4.2345. Min Range: -4.2345

Max Act: 3.0024. Min Act: -0.0000

Data Index: 545773 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 4.2345. Min Range: -4.2345

Max Act: 2.7116. Min Act: -0.0000

Data Index: 762484 (C4 (Web Text))

Max Activating Token Index: 615

Text #6

Max Range: 4.2345. Min Range: -4.2345

Max Act: 2.8464. Min Act: -0.0000

Data Index: 128017 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 4.2345. Min Range: -4.2345

Max Act: 2.6547. Min Act: -0.0000

Data Index: 984003 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 4.2345. Min Range: -4.2345

Max Act: 2.7643. Min Act: -0.0000

Data Index: 914488 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 4.2345. Min Range: -4.2345

Max Act: 2.7080. Min Act: -0.0000

Data Index: 1338106 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 4.2345. Min Range: -4.2345

Max Act: 2.4300. Min Act: -0.0000

Data Index: 630556 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 4.2345. Min Range: -4.2345

Max Act: 2.5149. Min Act: -0.0000

Data Index: 140899 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 4.2345. Min Range: -4.2345

Max Act: 2.5211. Min Act: -0.0000

Data Index: 681466 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 4.2345. Min Range: -4.2345

Max Act: 2.5009. Min Act: -0.0000

Data Index: 1060054 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 4.2345. Min Range: -4.2345

Max Act: 2.3716. Min Act: -0.0000

Data Index: 148052 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 4.2345. Min Range: -4.2345

Max Act: 2.6167. Min Act: -0.0000

Data Index: 873882 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 4.2345. Min Range: -4.2345

Max Act: 2.4667. Min Act: -0.0000

Data Index: 984781 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 4.2345. Min Range: -4.2345

Max Act: 2.2839. Min Act: -0.0000

Data Index: 793432 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 4.2345. Min Range: -4.2345

Max Act: 2.2581. Min Act: -0.0000

Data Index: 252024 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 4.2345. Min Range: -4.2345

Max Act: 2.3701. Min Act: -0.0000

Data Index: 363771 (C4 (Web Text))

Max Activating Token Index: 292