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

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

Neuron 4732 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0858. Min Range: -2.0858

Max Act: 1.9934. Min Act: -0.0000

Data Index: 1020272 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 2.0858. Min Range: -2.0858

Max Act: 2.0858. Min Act: -0.0000

Data Index: 783240 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 2.0858. Min Range: -2.0858

Max Act: 1.9062. Min Act: -0.0000

Data Index: 982099 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 2.0858. Min Range: -2.0858

Max Act: 1.8603. Min Act: -0.0000

Data Index: 330825 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 2.0858. Min Range: -2.0858

Max Act: 1.8847. Min Act: -0.0000

Data Index: 724073 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 2.0858. Min Range: -2.0858

Max Act: 1.9335. Min Act: -0.0000

Data Index: 534703 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 2.0858. Min Range: -2.0858

Max Act: 1.9027. Min Act: -0.0000

Data Index: 1125043 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 2.0858. Min Range: -2.0858

Max Act: 1.9675. Min Act: -0.0000

Data Index: 1310761 (C4 (Web Text))

Max Activating Token Index: 343

Text #8

Max Range: 2.0858. Min Range: -2.0858

Max Act: 1.9350. Min Act: -0.0000

Data Index: 1230583 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 2.0858. Min Range: -2.0858

Max Act: 1.7060. Min Act: -0.0000

Data Index: 1252820 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 2.0858. Min Range: -2.0858

Max Act: 1.8689. Min Act: -0.0000

Data Index: 370838 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 2.0858. Min Range: -2.0858

Max Act: 1.8925. Min Act: -0.0000

Data Index: 328 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 2.0858. Min Range: -2.0858

Max Act: 1.7744. Min Act: -0.0000

Data Index: 983786 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 2.0858. Min Range: -2.0858

Max Act: 1.7523. Min Act: -0.0000

Data Index: 458675 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 2.0858. Min Range: -2.0858

Max Act: 1.6382. Min Act: -0.0000

Data Index: 766990 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 2.0858. Min Range: -2.0858

Max Act: 1.6256. Min Act: -0.0000

Data Index: 914964 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 2.0858. Min Range: -2.0858

Max Act: 1.7290. Min Act: -0.0000

Data Index: 1341524 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 2.0858. Min Range: -2.0858

Max Act: 1.8251. Min Act: -0.0000

Data Index: 1114532 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 2.0858. Min Range: -2.0858

Max Act: 1.7323. Min Act: -0.0000

Data Index: 679846 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 2.0858. Min Range: -2.0858

Max Act: 1.8280. Min Act: -0.0000

Data Index: 134032 (C4 (Web Text))

Max Activating Token Index: 333