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

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

Neuron 3011 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: 1.6652. Min Range: -1.6652

Max Act: 1.6652. Min Act: -0.0002

Data Index: 1338172 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.5557. Min Act: -0.0002

Data Index: 1055988 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.4953. Min Act: -0.0002

Data Index: 1354910 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.4578. Min Act: -0.0002

Data Index: 1129901 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.4499. Min Act: -0.0002

Data Index: 36049 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.4258. Min Act: -0.0002

Data Index: 585319 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.4415. Min Act: -0.0002

Data Index: 778299 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.3472. Min Act: -0.0002

Data Index: 948281 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.3497. Min Act: -0.0002

Data Index: 1656414 (Python Code)

Max Activating Token Index: 272

Text #9

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.3518. Min Act: -0.0002

Data Index: 640894 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.2958. Min Act: -0.0002

Data Index: 476798 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.3737. Min Act: -0.0002

Data Index: 1220811 (C4 (Web Text))

Max Activating Token Index: 580

Text #12

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.3336. Min Act: -0.0002

Data Index: 119356 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.3217. Min Act: -0.0002

Data Index: 262780 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.3259. Min Act: -0.0002

Data Index: 566913 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.3122. Min Act: -0.0002

Data Index: 1309683 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.3096. Min Act: -0.0002

Data Index: 699342 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.2977. Min Act: -0.0002

Data Index: 772345 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.3042. Min Act: -0.0002

Data Index: 4133 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.3054. Min Act: -0.0002

Data Index: 1244966 (C4 (Web Text))

Max Activating Token Index: 786