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

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

Neuron 4644 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.6419. Min Act: -0.0000

Data Index: 883726 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.6642. Min Act: -0.0000

Data Index: 915323 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.6643. Min Act: -0.0000

Data Index: 1032566 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.6043. Min Act: -0.0000

Data Index: 252137 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.6121. Min Act: -0.0000

Data Index: 412800 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5856. Min Act: -0.0000

Data Index: 739218 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5488. Min Act: -0.0000

Data Index: 358765 (C4 (Web Text))

Max Activating Token Index: 178

Text #7

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.6038. Min Act: -0.0000

Data Index: 208803 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5263. Min Act: -0.0000

Data Index: 709215 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5806. Min Act: -0.0000

Data Index: 270094 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5716. Min Act: -0.0000

Data Index: 268075 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5825. Min Act: -0.0000

Data Index: 1019898 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5859. Min Act: -0.0000

Data Index: 1267688 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5214. Min Act: -0.0000

Data Index: 622465 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.4680. Min Act: -0.0000

Data Index: 797155 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5632. Min Act: -0.0000

Data Index: 471914 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5184. Min Act: -0.0000

Data Index: 1033428 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5165. Min Act: -0.0000

Data Index: 1241197 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5445. Min Act: -0.0000

Data Index: 803779 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.6510. Min Act: -0.0000

Data Index: 377214 (C4 (Web Text))

Max Activating Token Index: 798