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

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

Neuron 4525 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.3081. Min Act: -0.0000

Data Index: 455157 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2784. Min Act: -0.0000

Data Index: 974118 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2655. Min Act: -0.0000

Data Index: 843256 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2823. Min Act: -0.0000

Data Index: 729470 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2649. Min Act: -0.0000

Data Index: 282204 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2502. Min Act: -0.0000

Data Index: 681151 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2541. Min Act: -0.0000

Data Index: 931921 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2502. Min Act: -0.0000

Data Index: 31266 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2535. Min Act: -0.0000

Data Index: 1242124 (C4 (Web Text))

Max Activating Token Index: 474

Text #9

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2466. Min Act: -0.0000

Data Index: 908707 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2361. Min Act: -0.0000

Data Index: 660305 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2287. Min Act: -0.0000

Data Index: 75918 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2198. Min Act: -0.0000

Data Index: 529990 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2188. Min Act: -0.0000

Data Index: 44865 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2076. Min Act: -0.0000

Data Index: 87620 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2222. Min Act: -0.0000

Data Index: 176586 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2269. Min Act: -0.0000

Data Index: 131007 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2181. Min Act: -0.0000

Data Index: 1051649 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2186. Min Act: -0.0000

Data Index: 147773 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2180. Min Act: -0.0000

Data Index: 951719 (C4 (Web Text))

Max Activating Token Index: 458