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

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

Neuron 2257 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: 2.0706. Min Range: -2.0706

Max Act: 2.0706. Min Act: -0.0000

Data Index: 239241 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 2.0706. Min Range: -2.0706

Max Act: 1.9835. Min Act: -0.0000

Data Index: 345736 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 2.0706. Min Range: -2.0706

Max Act: 1.9506. Min Act: -0.0000

Data Index: 1252758 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 2.0706. Min Range: -2.0706

Max Act: 1.8126. Min Act: -0.0000

Data Index: 603521 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 2.0706. Min Range: -2.0706

Max Act: 1.7083. Min Act: -0.0000

Data Index: 1245996 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 2.0706. Min Range: -2.0706

Max Act: 1.7638. Min Act: -0.0000

Data Index: 483094 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 2.0706. Min Range: -2.0706

Max Act: 1.6700. Min Act: -0.0000

Data Index: 356106 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 2.0706. Min Range: -2.0706

Max Act: 1.6615. Min Act: -0.0000

Data Index: 664502 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 2.0706. Min Range: -2.0706

Max Act: 1.6234. Min Act: -0.0000

Data Index: 1330122 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 2.0706. Min Range: -2.0706

Max Act: 1.4344. Min Act: -0.0000

Data Index: 713076 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 2.0706. Min Range: -2.0706

Max Act: 1.5235. Min Act: -0.0000

Data Index: 192998 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 2.0706. Min Range: -2.0706

Max Act: 1.5108. Min Act: -0.0000

Data Index: 895846 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 2.0706. Min Range: -2.0706

Max Act: 1.3477. Min Act: -0.0000

Data Index: 1109901 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 2.0706. Min Range: -2.0706

Max Act: 1.4936. Min Act: -0.0000

Data Index: 607842 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 2.0706. Min Range: -2.0706

Max Act: 1.4700. Min Act: -0.0000

Data Index: 1225679 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 2.0706. Min Range: -2.0706

Max Act: 1.4662. Min Act: -0.0000

Data Index: 23953 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 2.0706. Min Range: -2.0706

Max Act: 1.4603. Min Act: -0.0000

Data Index: 1016205 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 2.0706. Min Range: -2.0706

Max Act: 1.3708. Min Act: -0.0000

Data Index: 119512 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 2.0706. Min Range: -2.0706

Max Act: 1.4409. Min Act: -0.0000

Data Index: 764890 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 2.0706. Min Range: -2.0706

Max Act: 1.4444. Min Act: -0.0000

Data Index: 275617 (C4 (Web Text))

Max Activating Token Index: 218