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

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

Neuron 1046 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.1751. Min Range: -1.1751

Max Act: 1.1751. Min Act: -0.0002

Data Index: 1001949 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 1.1751. Min Range: -1.1751

Max Act: 1.1659. Min Act: -0.0002

Data Index: 381495 (C4 (Web Text))

Max Activating Token Index: 530

Text #2

Max Range: 1.1751. Min Range: -1.1751

Max Act: 1.0770. Min Act: -0.0002

Data Index: 383689 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 1.1751. Min Range: -1.1751

Max Act: 1.0316. Min Act: -0.0003

Data Index: 700931 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 1.1751. Min Range: -1.1751

Max Act: 1.0420. Min Act: -0.0002

Data Index: 169243 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 1.1751. Min Range: -1.1751

Max Act: 1.0159. Min Act: -0.0002

Data Index: 424361 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 1.1751. Min Range: -1.1751

Max Act: 1.0086. Min Act: -0.0002

Data Index: 84783 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.9960. Min Act: -0.0002

Data Index: 281506 (C4 (Web Text))

Max Activating Token Index: 798

Text #8

Max Range: 1.1751. Min Range: -1.1751

Max Act: 1.0047. Min Act: -0.0002

Data Index: 309487 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.9795. Min Act: -0.0002

Data Index: 198107 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.9587. Min Act: -0.0003

Data Index: 1111806 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.9736. Min Act: -0.0002

Data Index: 197871 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.9625. Min Act: -0.0002

Data Index: 614781 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.9530. Min Act: -0.0002

Data Index: 122766 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.9480. Min Act: -0.0002

Data Index: 336083 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.9297. Min Act: -0.0002

Data Index: 1138577 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.9552. Min Act: -0.0002

Data Index: 919848 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.9342. Min Act: -0.0003

Data Index: 1125250 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.9339. Min Act: -0.0002

Data Index: 524136 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.9378. Min Act: -0.0002

Data Index: 323969 (C4 (Web Text))

Max Activating Token Index: 515