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

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

Neuron 4318 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1083. Min Range: -2.1083

Max Act: 2.1083. Min Act: -0.0000

Data Index: 615279 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 2.1083. Min Range: -2.1083

Max Act: 1.8635. Min Act: -0.0000

Data Index: 338410 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 2.1083. Min Range: -2.1083

Max Act: 1.7394. Min Act: -0.0000

Data Index: 1180044 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 2.1083. Min Range: -2.1083

Max Act: 1.7706. Min Act: -0.0000

Data Index: 771406 (C4 (Web Text))

Max Activating Token Index: 735

Text #4

Max Range: 2.1083. Min Range: -2.1083

Max Act: 1.7423. Min Act: -0.0000

Data Index: 367933 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 2.1083. Min Range: -2.1083

Max Act: 1.5731. Min Act: -0.0000

Data Index: 1278578 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 2.1083. Min Range: -2.1083

Max Act: 1.6360. Min Act: -0.0000

Data Index: 156482 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 2.1083. Min Range: -2.1083

Max Act: 1.5280. Min Act: -0.0000

Data Index: 29125 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 2.1083. Min Range: -2.1083

Max Act: 1.5467. Min Act: -0.0000

Data Index: 172048 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 2.1083. Min Range: -2.1083

Max Act: 1.5348. Min Act: -0.0000

Data Index: 734535 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 2.1083. Min Range: -2.1083

Max Act: 1.4768. Min Act: -0.0000

Data Index: 634192 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 2.1083. Min Range: -2.1083

Max Act: 1.5465. Min Act: -0.0000

Data Index: 610841 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 2.1083. Min Range: -2.1083

Max Act: 1.4987. Min Act: -0.0000

Data Index: 513263 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 2.1083. Min Range: -2.1083

Max Act: 1.4861. Min Act: -0.0000

Data Index: 1228312 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 2.1083. Min Range: -2.1083

Max Act: 1.4725. Min Act: -0.0000

Data Index: 690199 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 2.1083. Min Range: -2.1083

Max Act: 1.4774. Min Act: -0.0000

Data Index: 1029394 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 2.1083. Min Range: -2.1083

Max Act: 1.4694. Min Act: -0.0000

Data Index: 259304 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 2.1083. Min Range: -2.1083

Max Act: 1.4925. Min Act: -0.0000

Data Index: 1241314 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 2.1083. Min Range: -2.1083

Max Act: 1.5184. Min Act: -0.0000

Data Index: 596170 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 2.1083. Min Range: -2.1083

Max Act: 1.3140. Min Act: -0.0000

Data Index: 958841 (C4 (Web Text))

Max Activating Token Index: 1004