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

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

Neuron 2067 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.9037. Min Act: -0.0001

Data Index: 118492 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.7290. Min Act: -0.0000

Data Index: 876290 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6374. Min Act: -0.0001

Data Index: 386002 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6490. Min Act: -0.0000

Data Index: 1133776 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6042. Min Act: -0.0001

Data Index: 456470 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6428. Min Act: -0.0000

Data Index: 894731 (C4 (Web Text))

Max Activating Token Index: 642

Text #6

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6263. Min Act: -0.0000

Data Index: 61887 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.5563. Min Act: -0.0000

Data Index: 1156611 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.5647. Min Act: -0.0001

Data Index: 1229902 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.5284. Min Act: -0.0000

Data Index: 1041997 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.5036. Min Act: -0.0000

Data Index: 910290 (C4 (Web Text))

Max Activating Token Index: 347

Text #11

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.4903. Min Act: -0.0000

Data Index: 838529 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.4500. Min Act: -0.0000

Data Index: 237833 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.4938. Min Act: -0.0000

Data Index: 369599 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.4461. Min Act: -0.0000

Data Index: 1317750 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.4591. Min Act: -0.0000

Data Index: 557221 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.4298. Min Act: -0.0001

Data Index: 276284 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.4278. Min Act: -0.0000

Data Index: 784891 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.4105. Min Act: -0.0000

Data Index: 1236688 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.4319. Min Act: -0.0000

Data Index: 1151130 (C4 (Web Text))

Max Activating Token Index: 185