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

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

Neuron 2112 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.7598. Min Act: -0.0000

Data Index: 407283 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.6542. Min Act: -0.0000

Data Index: 853469 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.7051. Min Act: -0.0000

Data Index: 1210531 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.6704. Min Act: -0.0000

Data Index: 1190696 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.3098. Min Act: -0.0000

Data Index: 473426 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.2589. Min Act: -0.0000

Data Index: 987331 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.3287. Min Act: -0.0000

Data Index: 652762 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.3402. Min Act: -0.0000

Data Index: 941434 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.2849. Min Act: -0.0000

Data Index: 539274 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.3448. Min Act: -0.0000

Data Index: 1339615 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.2324. Min Act: -0.0000

Data Index: 1337981 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.2652. Min Act: -0.0000

Data Index: 150288 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.2650. Min Act: -0.0000

Data Index: 1323239 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.1732. Min Act: -0.0000

Data Index: 783584 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.1945. Min Act: -0.0000

Data Index: 656385 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.1674. Min Act: -0.0000

Data Index: 1130585 (C4 (Web Text))

Max Activating Token Index: 473

Text #16

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.1899. Min Act: -0.0000

Data Index: 1180919 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.1383. Min Act: -0.0000

Data Index: 1197385 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.0788. Min Act: -0.0000

Data Index: 716308 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.0794. Min Act: -0.0000

Data Index: 280203 (C4 (Web Text))

Max Activating Token Index: 103