Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5337 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2579. Min Act: -0.0001

Data Index: 107703 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2331. Min Act: -0.0001

Data Index: 797543 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2341. Min Act: -0.0001

Data Index: 271033 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2389. Min Act: -0.0001

Data Index: 124503 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2367. Min Act: -0.0001

Data Index: 1049203 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2236. Min Act: -0.0001

Data Index: 1134896 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2191. Min Act: -0.0001

Data Index: 262763 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2183. Min Act: -0.0001

Data Index: 1003613 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2118. Min Act: -0.0001

Data Index: 253185 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2174. Min Act: -0.0001

Data Index: 1346034 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2076. Min Act: -0.0002

Data Index: 936828 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.1795. Min Act: -0.0001

Data Index: 739036 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2255. Min Act: -0.0001

Data Index: 246049 (C4 (Web Text))

Max Activating Token Index: 437

Text #13

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2330. Min Act: -0.0001

Data Index: 289298 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2168. Min Act: -0.0001

Data Index: 806811 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2275. Min Act: -0.0001

Data Index: 400447 (C4 (Web Text))

Max Activating Token Index: 639

Text #16

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.1915. Min Act: -0.0001

Data Index: 858334 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.1877. Min Act: -0.0001

Data Index: 830435 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.1924. Min Act: -0.0001

Data Index: 275144 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 0.2579. Min Range: -0.2579

Max Act: 0.2047. Min Act: -0.0001

Data Index: 927768 (C4 (Web Text))

Max Activating Token Index: 993