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

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

Neuron 4718 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3039. Min Range: -5.3039

Max Act: 5.3039. Min Act: -0.0000

Data Index: 1164526 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 5.3039. Min Range: -5.3039

Max Act: 5.1415. Min Act: -0.0000

Data Index: 624489 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 5.3039. Min Range: -5.3039

Max Act: 5.1156. Min Act: -0.0000

Data Index: 448718 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 5.3039. Min Range: -5.3039

Max Act: 4.7404. Min Act: -0.0000

Data Index: 1253306 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 5.3039. Min Range: -5.3039

Max Act: 4.8705. Min Act: -0.0000

Data Index: 878324 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 5.3039. Min Range: -5.3039

Max Act: 4.7257. Min Act: -0.0000

Data Index: 154307 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 5.3039. Min Range: -5.3039

Max Act: 4.8945. Min Act: -0.0000

Data Index: 209028 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 5.3039. Min Range: -5.3039

Max Act: 4.2905. Min Act: -0.0000

Data Index: 719364 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 5.3039. Min Range: -5.3039

Max Act: 4.2387. Min Act: -0.0000

Data Index: 816120 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 5.3039. Min Range: -5.3039

Max Act: 4.3812. Min Act: -0.0000

Data Index: 1167599 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 5.3039. Min Range: -5.3039

Max Act: 4.6238. Min Act: -0.0000

Data Index: 13728 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 5.3039. Min Range: -5.3039

Max Act: 4.4416. Min Act: -0.0000

Data Index: 142868 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 5.3039. Min Range: -5.3039

Max Act: 4.1825. Min Act: -0.0000

Data Index: 805535 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 5.3039. Min Range: -5.3039

Max Act: 4.3300. Min Act: -0.0000

Data Index: 557306 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 5.3039. Min Range: -5.3039

Max Act: 3.8207. Min Act: -0.0000

Data Index: 1088334 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 5.3039. Min Range: -5.3039

Max Act: 3.9050. Min Act: -0.0000

Data Index: 465050 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 5.3039. Min Range: -5.3039

Max Act: 3.9822. Min Act: -0.0000

Data Index: 147234 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 5.3039. Min Range: -5.3039

Max Act: 3.6224. Min Act: -0.0000

Data Index: 1339447 (C4 (Web Text))

Max Activating Token Index: 984

Text #18

Max Range: 5.3039. Min Range: -5.3039

Max Act: 3.3226. Min Act: -0.0000

Data Index: 383491 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 5.3039. Min Range: -5.3039

Max Act: 3.2946. Min Act: -0.0000

Data Index: 796379 (C4 (Web Text))

Max Activating Token Index: 243