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

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

Neuron 3607 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.5389. Min Range: -6.5389

Max Act: 6.5389. Min Act: -0.0000

Data Index: 958252 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 6.5389. Min Range: -6.5389

Max Act: 5.7531. Min Act: -0.0000

Data Index: 463766 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 6.5389. Min Range: -6.5389

Max Act: 6.1726. Min Act: -0.0000

Data Index: 1211862 (C4 (Web Text))

Max Activating Token Index: 332

Text #3

Max Range: 6.5389. Min Range: -6.5389

Max Act: 6.3309. Min Act: -0.0000

Data Index: 747510 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 6.5389. Min Range: -6.5389

Max Act: 6.0802. Min Act: -0.0000

Data Index: 800183 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 6.5389. Min Range: -6.5389

Max Act: 6.4451. Min Act: -0.0000

Data Index: 193306 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 6.5389. Min Range: -6.5389

Max Act: 5.9755. Min Act: -0.0000

Data Index: 128732 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 6.5389. Min Range: -6.5389

Max Act: 5.3872. Min Act: -0.0000

Data Index: 720036 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 6.5389. Min Range: -6.5389

Max Act: 6.1406. Min Act: -0.0000

Data Index: 1230750 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 6.5389. Min Range: -6.5389

Max Act: 5.3600. Min Act: -0.0000

Data Index: 1232808 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 6.5389. Min Range: -6.5389

Max Act: 5.5162. Min Act: -0.0000

Data Index: 137734 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 6.5389. Min Range: -6.5389

Max Act: 5.0846. Min Act: -0.0000

Data Index: 1042763 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 6.5389. Min Range: -6.5389

Max Act: 5.5569. Min Act: -0.0000

Data Index: 6875 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 6.5389. Min Range: -6.5389

Max Act: 5.4679. Min Act: -0.0000

Data Index: 350010 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 6.5389. Min Range: -6.5389

Max Act: 5.0475. Min Act: -0.0000

Data Index: 792584 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 6.5389. Min Range: -6.5389

Max Act: 5.2819. Min Act: -0.0000

Data Index: 1261543 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 6.5389. Min Range: -6.5389

Max Act: 5.1752. Min Act: -0.0000

Data Index: 1150225 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 6.5389. Min Range: -6.5389

Max Act: 4.9593. Min Act: -0.0000

Data Index: 513124 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 6.5389. Min Range: -6.5389

Max Act: 5.1114. Min Act: -0.0000

Data Index: 589627 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 6.5389. Min Range: -6.5389

Max Act: 4.8561. Min Act: -0.0000

Data Index: 809100 (C4 (Web Text))

Max Activating Token Index: 616