Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3609 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0375. Min Range: -1.0375

Max Act: 1.0375. Min Act: -0.0001

Data Index: 706793 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.9002. Min Act: -0.0001

Data Index: 255655 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.9306. Min Act: -0.0001

Data Index: 1254951 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.8741. Min Act: -0.0001

Data Index: 44448 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.9021. Min Act: -0.0001

Data Index: 1095293 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.8925. Min Act: -0.0001

Data Index: 171258 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.8522. Min Act: -0.0001

Data Index: 1027326 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.7807. Min Act: -0.0001

Data Index: 801411 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.8283. Min Act: -0.0001

Data Index: 1269644 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.7887. Min Act: -0.0001

Data Index: 699662 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.7596. Min Act: -0.0001

Data Index: 124191 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.7292. Min Act: -0.0001

Data Index: 180659 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.7569. Min Act: -0.0001

Data Index: 413314 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.7270. Min Act: -0.0001

Data Index: 327518 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.7434. Min Act: -0.0001

Data Index: 1248343 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.6919. Min Act: -0.0001

Data Index: 1205437 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.7288. Min Act: -0.0001

Data Index: 1265310 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.6912. Min Act: -0.0001

Data Index: 779924 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.6959. Min Act: -0.0001

Data Index: 15812 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.6474. Min Act: -0.0001

Data Index: 441223 (C4 (Web Text))

Max Activating Token Index: 337