Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 514 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0597. Min Act: -0.0005

Data Index: 137472 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0555. Min Act: -0.0005

Data Index: 1002193 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0563. Min Act: -0.0005

Data Index: 857116 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0536. Min Act: -0.0004

Data Index: 692060 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0550. Min Act: -0.0005

Data Index: 1161691 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0521. Min Act: -0.0005

Data Index: 586405 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0545. Min Act: -0.0005

Data Index: 698441 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0516. Min Act: -0.0005

Data Index: 1062137 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0517. Min Act: -0.0005

Data Index: 1047228 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0506. Min Act: -0.0005

Data Index: 1326231 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0487. Min Act: -0.0005

Data Index: 941520 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0485. Min Act: -0.0005

Data Index: 1311826 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0510. Min Act: -0.0005

Data Index: 670197 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0489. Min Act: -0.0005

Data Index: 166618 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0473. Min Act: -0.0005

Data Index: 314183 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0479. Min Act: -0.0005

Data Index: 387170 (C4 (Web Text))

Max Activating Token Index: 722

Text #16

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0494. Min Act: -0.0005

Data Index: 687158 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0486. Min Act: -0.0005

Data Index: 52799 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0486. Min Act: -0.0004

Data Index: 524174 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0464. Min Act: -0.0005

Data Index: 62923 (C4 (Web Text))

Max Activating Token Index: 326