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

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

Neuron 256 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: 2.2158. Min Range: -2.2158

Max Act: 2.0939. Min Act: -0.0000

Data Index: 1294676 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 2.2158. Min Range: -2.2158

Max Act: 2.2158. Min Act: -0.0000

Data Index: 160879 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 2.2158. Min Range: -2.2158

Max Act: 1.8360. Min Act: -0.0000

Data Index: 204996 (C4 (Web Text))

Max Activating Token Index: 450

Text #3

Max Range: 2.2158. Min Range: -2.2158

Max Act: 1.6356. Min Act: -0.0000

Data Index: 369466 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 2.2158. Min Range: -2.2158

Max Act: 1.5989. Min Act: -0.0001

Data Index: 1027349 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 2.2158. Min Range: -2.2158

Max Act: 1.2404. Min Act: -0.0000

Data Index: 496605 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 2.2158. Min Range: -2.2158

Max Act: 1.1919. Min Act: -0.0000

Data Index: 69769 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 2.2158. Min Range: -2.2158

Max Act: 1.0545. Min Act: -0.0000

Data Index: 1216160 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 2.2158. Min Range: -2.2158

Max Act: 1.0601. Min Act: -0.0001

Data Index: 1610383 (Python Code)

Max Activating Token Index: 659

Text #9

Max Range: 2.2158. Min Range: -2.2158

Max Act: 1.0893. Min Act: -0.0001

Data Index: 1194029 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 2.2158. Min Range: -2.2158

Max Act: 1.1143. Min Act: -0.0000

Data Index: 785122 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 2.2158. Min Range: -2.2158

Max Act: 1.0002. Min Act: -0.0000

Data Index: 61042 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 2.2158. Min Range: -2.2158

Max Act: 0.9987. Min Act: -0.0000

Data Index: 643815 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 2.2158. Min Range: -2.2158

Max Act: 1.0828. Min Act: -0.0000

Data Index: 370059 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 2.2158. Min Range: -2.2158

Max Act: 1.0705. Min Act: -0.0000

Data Index: 1118294 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 2.2158. Min Range: -2.2158

Max Act: 0.8919. Min Act: -0.0000

Data Index: 588158 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 2.2158. Min Range: -2.2158

Max Act: 1.0872. Min Act: -0.0000

Data Index: 573303 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 2.2158. Min Range: -2.2158

Max Act: 1.0902. Min Act: -0.0000

Data Index: 149947 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 2.2158. Min Range: -2.2158

Max Act: 1.0453. Min Act: -0.0000

Data Index: 719867 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 2.2158. Min Range: -2.2158

Max Act: 1.0452. Min Act: -0.0000

Data Index: 112302 (C4 (Web Text))

Max Activating Token Index: 16