Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4293 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.5812. Min Act: -0.0001

Data Index: 959740 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.5765. Min Act: -0.0001

Data Index: 500640 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.5370. Min Act: -0.0001

Data Index: 689898 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.6040. Min Act: -0.0001

Data Index: 376755 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.5705. Min Act: -0.0001

Data Index: 624617 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.4779. Min Act: -0.0001

Data Index: 1010486 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.5406. Min Act: -0.0001

Data Index: 1114028 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.4620. Min Act: -0.0001

Data Index: 1229628 (C4 (Web Text))

Max Activating Token Index: 206

Text #8

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.4502. Min Act: -0.0001

Data Index: 269685 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.4731. Min Act: -0.0000

Data Index: 557627 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.5062. Min Act: -0.0001

Data Index: 1155670 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.4744. Min Act: -0.0001

Data Index: 674389 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.5204. Min Act: -0.0001

Data Index: 1255332 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.4683. Min Act: -0.0001

Data Index: 1152615 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.5140. Min Act: -0.0001

Data Index: 23405 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.4908. Min Act: -0.0001

Data Index: 1336854 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.6080. Min Act: -0.0001

Data Index: 1166966 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.4004. Min Act: -0.0001

Data Index: 359617 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.4600. Min Act: -0.0001

Data Index: 159057 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.4185. Min Act: -0.0001

Data Index: 136226 (C4 (Web Text))

Max Activating Token Index: 21