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

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

Neuron 5384 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: 1.6937. Min Range: -1.6937

Max Act: 1.6937. Min Act: -0.0001

Data Index: 1258993 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.3940. Min Act: -0.0001

Data Index: 1084575 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.3019. Min Act: -0.0001

Data Index: 372613 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.2668. Min Act: -0.0001

Data Index: 787371 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.3664. Min Act: -0.0001

Data Index: 996484 (C4 (Web Text))

Max Activating Token Index: 324

Text #5

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.2361. Min Act: -0.0001

Data Index: 938747 (C4 (Web Text))

Max Activating Token Index: 533

Text #6

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.3737. Min Act: -0.0001

Data Index: 313030 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.2113. Min Act: -0.0001

Data Index: 552626 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.3080. Min Act: -0.0001

Data Index: 166856 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.2864. Min Act: -0.0001

Data Index: 706817 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.2372. Min Act: -0.0001

Data Index: 770633 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.1663. Min Act: -0.0001

Data Index: 1313695 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.2001. Min Act: -0.0001

Data Index: 615662 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.0952. Min Act: -0.0001

Data Index: 580790 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.1129. Min Act: -0.0000

Data Index: 1453772 (Python Code)

Max Activating Token Index: 195

Text #15

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.1224. Min Act: -0.0001

Data Index: 152496 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.1198. Min Act: -0.0001

Data Index: 1344574 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.1306. Min Act: -0.0001

Data Index: 949868 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.0715. Min Act: -0.0000

Data Index: 1067845 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.0362. Min Act: -0.0001

Data Index: 10516 (C4 (Web Text))

Max Activating Token Index: 720