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

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

Neuron 3657 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1187. Min Range: -1.1187

Max Act: 1.1187. Min Act: -0.0001

Data Index: 1293633 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.9427. Min Act: -0.0001

Data Index: 387602 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.9267. Min Act: -0.0001

Data Index: 1236741 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.7738. Min Act: -0.0001

Data Index: 471204 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.8712. Min Act: -0.0001

Data Index: 177569 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.8526. Min Act: -0.0001

Data Index: 228446 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.7606. Min Act: -0.0001

Data Index: 250477 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.7484. Min Act: -0.0001

Data Index: 264140 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.7124. Min Act: -0.0000

Data Index: 1157875 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.6812. Min Act: -0.0000

Data Index: 584384 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.6751. Min Act: -0.0000

Data Index: 1307017 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.6208. Min Act: -0.0000

Data Index: 249684 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.6603. Min Act: -0.0001

Data Index: 407690 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.6360. Min Act: -0.0001

Data Index: 132801 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.5900. Min Act: -0.0001

Data Index: 1285311 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.6483. Min Act: -0.0001

Data Index: 55964 (C4 (Web Text))

Max Activating Token Index: 970

Text #16

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.5948. Min Act: -0.0000

Data Index: 968066 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.5740. Min Act: -0.0001

Data Index: 1212523 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.5981. Min Act: -0.0000

Data Index: 98302 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.5856. Min Act: -0.0000

Data Index: 359784 (C4 (Web Text))

Max Activating Token Index: 797