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

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

Neuron 4067 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3769. Min Range: -2.3769

Max Act: 2.3769. Min Act: -0.0000

Data Index: 1306602 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 2.3769. Min Range: -2.3769

Max Act: 2.1713. Min Act: -0.0001

Data Index: 571969 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 2.3769. Min Range: -2.3769

Max Act: 2.2361. Min Act: -0.0000

Data Index: 513401 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 2.3769. Min Range: -2.3769

Max Act: 2.1400. Min Act: -0.0001

Data Index: 1182186 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 2.3769. Min Range: -2.3769

Max Act: 1.9180. Min Act: -0.0001

Data Index: 974135 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 2.3769. Min Range: -2.3769

Max Act: 2.0945. Min Act: -0.0001

Data Index: 1020342 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 2.3769. Min Range: -2.3769

Max Act: 1.8899. Min Act: -0.0001

Data Index: 1256284 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 2.3769. Min Range: -2.3769

Max Act: 2.0529. Min Act: -0.0001

Data Index: 1110304 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 2.3769. Min Range: -2.3769

Max Act: 1.7602. Min Act: -0.0000

Data Index: 873213 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 2.3769. Min Range: -2.3769

Max Act: 1.9243. Min Act: -0.0000

Data Index: 832648 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 2.3769. Min Range: -2.3769

Max Act: 1.8021. Min Act: -0.0001

Data Index: 784488 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 2.3769. Min Range: -2.3769

Max Act: 1.8274. Min Act: -0.0001

Data Index: 742610 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 2.3769. Min Range: -2.3769

Max Act: 1.7182. Min Act: -0.0001

Data Index: 532076 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 2.3769. Min Range: -2.3769

Max Act: 1.7387. Min Act: -0.0000

Data Index: 119466 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 2.3769. Min Range: -2.3769

Max Act: 1.8004. Min Act: -0.0001

Data Index: 863377 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 2.3769. Min Range: -2.3769

Max Act: 1.7573. Min Act: -0.0000

Data Index: 215069 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 2.3769. Min Range: -2.3769

Max Act: 1.7733. Min Act: -0.0001

Data Index: 171229 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 2.3769. Min Range: -2.3769

Max Act: 1.7562. Min Act: -0.0001

Data Index: 338582 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 2.3769. Min Range: -2.3769

Max Act: 1.8606. Min Act: -0.0000

Data Index: 332613 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 2.3769. Min Range: -2.3769

Max Act: 1.7463. Min Act: -0.0000

Data Index: 928403 (C4 (Web Text))

Max Activating Token Index: 867