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

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

Neuron 3900 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.2135. Min Range: -6.2135

Max Act: 6.2135. Min Act: -0.0000

Data Index: 533683 (C4 (Web Text))

Max Activating Token Index: 490

Text #1

Max Range: 6.2135. Min Range: -6.2135

Max Act: 5.4453. Min Act: -0.0000

Data Index: 96851 (C4 (Web Text))

Max Activating Token Index: 380

Text #2

Max Range: 6.2135. Min Range: -6.2135

Max Act: 5.1271. Min Act: -0.0000

Data Index: 193947 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 6.2135. Min Range: -6.2135

Max Act: 4.4937. Min Act: -0.0000

Data Index: 457419 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 6.2135. Min Range: -6.2135

Max Act: 4.6317. Min Act: -0.0000

Data Index: 101951 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 6.2135. Min Range: -6.2135

Max Act: 4.5680. Min Act: -0.0000

Data Index: 438421 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 6.2135. Min Range: -6.2135

Max Act: 4.7627. Min Act: -0.0000

Data Index: 353529 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 6.2135. Min Range: -6.2135

Max Act: 4.2353. Min Act: -0.0000

Data Index: 220194 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 6.2135. Min Range: -6.2135

Max Act: 4.5659. Min Act: -0.0000

Data Index: 335719 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 6.2135. Min Range: -6.2135

Max Act: 4.3620. Min Act: -0.0000

Data Index: 674152 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 6.2135. Min Range: -6.2135

Max Act: 4.3213. Min Act: -0.0000

Data Index: 1041063 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 6.2135. Min Range: -6.2135

Max Act: 4.2984. Min Act: -0.0000

Data Index: 1147726 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 6.2135. Min Range: -6.2135

Max Act: 4.0203. Min Act: -0.0000

Data Index: 627113 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 6.2135. Min Range: -6.2135

Max Act: 4.3963. Min Act: -0.0000

Data Index: 806200 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 6.2135. Min Range: -6.2135

Max Act: 3.9923. Min Act: -0.0000

Data Index: 502829 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 6.2135. Min Range: -6.2135

Max Act: 4.0124. Min Act: -0.0000

Data Index: 534991 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 6.2135. Min Range: -6.2135

Max Act: 4.1166. Min Act: -0.0000

Data Index: 790434 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 6.2135. Min Range: -6.2135

Max Act: 3.9148. Min Act: -0.0000

Data Index: 104066 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 6.2135. Min Range: -6.2135

Max Act: 4.0987. Min Act: -0.0000

Data Index: 776851 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 6.2135. Min Range: -6.2135

Max Act: 4.1294. Min Act: -0.0000

Data Index: 180189 (C4 (Web Text))

Max Activating Token Index: 990