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

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

Neuron 3944 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3545. Min Range: -3.3545

Max Act: 3.3545. Min Act: -0.0001

Data Index: 628811 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 3.3545. Min Range: -3.3545

Max Act: 3.1543. Min Act: -0.0000

Data Index: 200436 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 3.3545. Min Range: -3.3545

Max Act: 2.8882. Min Act: -0.0000

Data Index: 1332642 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 3.3545. Min Range: -3.3545

Max Act: 2.9972. Min Act: -0.0001

Data Index: 458491 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 3.3545. Min Range: -3.3545

Max Act: 2.9561. Min Act: -0.0001

Data Index: 790279 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 3.3545. Min Range: -3.3545

Max Act: 2.6194. Min Act: -0.0001

Data Index: 622602 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 3.3545. Min Range: -3.3545

Max Act: 2.6776. Min Act: -0.0001

Data Index: 996708 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 3.3545. Min Range: -3.3545

Max Act: 2.5087. Min Act: -0.0001

Data Index: 881214 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 3.3545. Min Range: -3.3545

Max Act: 2.7509. Min Act: -0.0001

Data Index: 1009373 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 3.3545. Min Range: -3.3545

Max Act: 2.6098. Min Act: -0.0001

Data Index: 593595 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 3.3545. Min Range: -3.3545

Max Act: 2.5648. Min Act: -0.0001

Data Index: 377062 (C4 (Web Text))

Max Activating Token Index: 725

Text #11

Max Range: 3.3545. Min Range: -3.3545

Max Act: 2.4441. Min Act: -0.0001

Data Index: 1294828 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 3.3545. Min Range: -3.3545

Max Act: 2.4331. Min Act: -0.0001

Data Index: 876961 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 3.3545. Min Range: -3.3545

Max Act: 2.5349. Min Act: -0.0000

Data Index: 227434 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 3.3545. Min Range: -3.3545

Max Act: 2.4294. Min Act: -0.0001

Data Index: 608670 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 3.3545. Min Range: -3.3545

Max Act: 2.4932. Min Act: -0.0001

Data Index: 1359447 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 3.3545. Min Range: -3.3545

Max Act: 2.4677. Min Act: -0.0001

Data Index: 382170 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 3.3545. Min Range: -3.3545

Max Act: 2.4697. Min Act: -0.0001

Data Index: 527249 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 3.3545. Min Range: -3.3545

Max Act: 2.4241. Min Act: -0.0001

Data Index: 1193598 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 3.3545. Min Range: -3.3545

Max Act: 2.4252. Min Act: -0.0000

Data Index: 60219 (C4 (Web Text))

Max Activating Token Index: 737