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

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

Neuron 5240 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2942. Min Range: -2.2942

Max Act: 2.2942. Min Act: -0.0000

Data Index: 1132540 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 2.2942. Min Range: -2.2942

Max Act: 2.2708. Min Act: -0.0000

Data Index: 881860 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 2.2942. Min Range: -2.2942

Max Act: 2.1852. Min Act: -0.0000

Data Index: 679080 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 2.2942. Min Range: -2.2942

Max Act: 2.2467. Min Act: -0.0000

Data Index: 515941 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 2.2942. Min Range: -2.2942

Max Act: 1.9642. Min Act: -0.0000

Data Index: 176435 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 2.2942. Min Range: -2.2942

Max Act: 2.0589. Min Act: -0.0000

Data Index: 867214 (C4 (Web Text))

Max Activating Token Index: 615

Text #6

Max Range: 2.2942. Min Range: -2.2942

Max Act: 2.0258. Min Act: -0.0000

Data Index: 556350 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 2.2942. Min Range: -2.2942

Max Act: 2.0405. Min Act: -0.0000

Data Index: 95016 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 2.2942. Min Range: -2.2942

Max Act: 2.0314. Min Act: -0.0000

Data Index: 1056529 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 2.2942. Min Range: -2.2942

Max Act: 2.0341. Min Act: -0.0000

Data Index: 90092 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 2.2942. Min Range: -2.2942

Max Act: 1.8840. Min Act: -0.0000

Data Index: 968654 (C4 (Web Text))

Max Activating Token Index: 797

Text #11

Max Range: 2.2942. Min Range: -2.2942

Max Act: 2.0913. Min Act: -0.0000

Data Index: 424099 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 2.2942. Min Range: -2.2942

Max Act: 1.9989. Min Act: -0.0000

Data Index: 336482 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 2.2942. Min Range: -2.2942

Max Act: 1.8679. Min Act: -0.0000

Data Index: 1326293 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 2.2942. Min Range: -2.2942

Max Act: 1.8475. Min Act: -0.0000

Data Index: 36174 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 2.2942. Min Range: -2.2942

Max Act: 1.9468. Min Act: -0.0000

Data Index: 231822 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 2.2942. Min Range: -2.2942

Max Act: 1.9031. Min Act: -0.0000

Data Index: 449246 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 2.2942. Min Range: -2.2942

Max Act: 1.8814. Min Act: -0.0000

Data Index: 530567 (C4 (Web Text))

Max Activating Token Index: 509

Text #18

Max Range: 2.2942. Min Range: -2.2942

Max Act: 1.8954. Min Act: -0.0000

Data Index: 123087 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 2.2942. Min Range: -2.2942

Max Act: 2.0077. Min Act: -0.0000

Data Index: 1248971 (C4 (Web Text))

Max Activating Token Index: 881