Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 250 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8882. Min Range: -0.8882

Max Act: 0.8882. Min Act: -0.0001

Data Index: 1063790 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 0.8882. Min Range: -0.8882

Max Act: 0.8005. Min Act: -0.0001

Data Index: 887307 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 0.8882. Min Range: -0.8882

Max Act: 0.7955. Min Act: -0.0001

Data Index: 397018 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 0.8882. Min Range: -0.8882

Max Act: 0.7860. Min Act: -0.0000

Data Index: 1321730 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 0.8882. Min Range: -0.8882

Max Act: 0.8243. Min Act: -0.0001

Data Index: 1071206 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 0.8882. Min Range: -0.8882

Max Act: 0.7719. Min Act: -0.0000

Data Index: 912179 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 0.8882. Min Range: -0.8882

Max Act: 0.7696. Min Act: -0.0001

Data Index: 1069641 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 0.8882. Min Range: -0.8882

Max Act: 0.7626. Min Act: -0.0001

Data Index: 281584 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 0.8882. Min Range: -0.8882

Max Act: 0.7784. Min Act: -0.0000

Data Index: 49223 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 0.8882. Min Range: -0.8882

Max Act: 0.7639. Min Act: -0.0001

Data Index: 246099 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 0.8882. Min Range: -0.8882

Max Act: 0.7630. Min Act: -0.0001

Data Index: 590056 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 0.8882. Min Range: -0.8882

Max Act: 0.7383. Min Act: -0.0001

Data Index: 676915 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 0.8882. Min Range: -0.8882

Max Act: 0.7596. Min Act: -0.0001

Data Index: 665535 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 0.8882. Min Range: -0.8882

Max Act: 0.7481. Min Act: -0.0001

Data Index: 877603 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 0.8882. Min Range: -0.8882

Max Act: 0.7436. Min Act: -0.0001

Data Index: 820980 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 0.8882. Min Range: -0.8882

Max Act: 0.7120. Min Act: -0.0001

Data Index: 1135556 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 0.8882. Min Range: -0.8882

Max Act: 0.7026. Min Act: -0.0000

Data Index: 105529 (C4 (Web Text))

Max Activating Token Index: 326

Text #17

Max Range: 0.8882. Min Range: -0.8882

Max Act: 0.7024. Min Act: -0.0001

Data Index: 94662 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 0.8882. Min Range: -0.8882

Max Act: 0.7177. Min Act: -0.0001

Data Index: 793095 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 0.8882. Min Range: -0.8882

Max Act: 0.7152. Min Act: -0.0001

Data Index: 584245 (C4 (Web Text))

Max Activating Token Index: 548