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

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

Neuron 1299 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0616. Min Range: -1.0616

Max Act: 1.0616. Min Act: -0.0000

Data Index: 324957 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.9695. Min Act: -0.0000

Data Index: 644530 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.9129. Min Act: -0.0000

Data Index: 117372 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.9514. Min Act: -0.0000

Data Index: 1355188 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.9782. Min Act: -0.0000

Data Index: 420530 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.8108. Min Act: -0.0000

Data Index: 632140 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.7886. Min Act: -0.0000

Data Index: 333045 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.7369. Min Act: -0.0000

Data Index: 217731 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.7163. Min Act: -0.0000

Data Index: 927298 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.6983. Min Act: -0.0000

Data Index: 1216962 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.6420. Min Act: -0.0000

Data Index: 826036 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.6789. Min Act: -0.0000

Data Index: 1326583 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.7256. Min Act: -0.0000

Data Index: 1266405 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.6096. Min Act: -0.0000

Data Index: 517425 (C4 (Web Text))

Max Activating Token Index: 352

Text #14

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.6004. Min Act: -0.0000

Data Index: 1656536 (Python Code)

Max Activating Token Index: 178

Text #15

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.5161. Min Act: -0.0000

Data Index: 914685 (C4 (Web Text))

Max Activating Token Index: 321

Text #16

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.4920. Min Act: -0.0000

Data Index: 592037 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.5067. Min Act: -0.0000

Data Index: 619467 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.5496. Min Act: -0.0000

Data Index: 906737 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.5713. Min Act: -0.0000

Data Index: 432160 (C4 (Web Text))

Max Activating Token Index: 283