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

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

Neuron 2733 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: 1.9707. Min Range: -1.9707

Max Act: 1.9707. Min Act: -0.0001

Data Index: 1204241 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 1.9707. Min Range: -1.9707

Max Act: 1.7933. Min Act: -0.0001

Data Index: 233151 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 1.9707. Min Range: -1.9707

Max Act: 1.5166. Min Act: -0.0001

Data Index: 998292 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 1.9707. Min Range: -1.9707

Max Act: 1.5153. Min Act: -0.0001

Data Index: 1184997 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 1.9707. Min Range: -1.9707

Max Act: 1.6736. Min Act: -0.0001

Data Index: 1150801 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 1.9707. Min Range: -1.9707

Max Act: 1.5658. Min Act: -0.0001

Data Index: 383472 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 1.9707. Min Range: -1.9707

Max Act: 1.5740. Min Act: -0.0001

Data Index: 926102 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 1.9707. Min Range: -1.9707

Max Act: 1.6544. Min Act: -0.0001

Data Index: 987774 (C4 (Web Text))

Max Activating Token Index: 729

Text #8

Max Range: 1.9707. Min Range: -1.9707

Max Act: 1.6204. Min Act: -0.0001

Data Index: 1202780 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 1.9707. Min Range: -1.9707

Max Act: 1.5336. Min Act: -0.0001

Data Index: 1043150 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 1.9707. Min Range: -1.9707

Max Act: 1.4439. Min Act: -0.0001

Data Index: 333275 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 1.9707. Min Range: -1.9707

Max Act: 1.3422. Min Act: -0.0000

Data Index: 916834 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 1.9707. Min Range: -1.9707

Max Act: 1.3721. Min Act: -0.0000

Data Index: 491342 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 1.9707. Min Range: -1.9707

Max Act: 1.4396. Min Act: -0.0001

Data Index: 422739 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 1.9707. Min Range: -1.9707

Max Act: 1.3670. Min Act: -0.0000

Data Index: 73576 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 1.9707. Min Range: -1.9707

Max Act: 1.3166. Min Act: -0.0001

Data Index: 432373 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 1.9707. Min Range: -1.9707

Max Act: 1.3798. Min Act: -0.0001

Data Index: 934795 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 1.9707. Min Range: -1.9707

Max Act: 1.3493. Min Act: -0.0001

Data Index: 1279901 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 1.9707. Min Range: -1.9707

Max Act: 1.4064. Min Act: -0.0001

Data Index: 336063 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 1.9707. Min Range: -1.9707

Max Act: 1.3605. Min Act: -0.0001

Data Index: 724307 (C4 (Web Text))

Max Activating Token Index: 899