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

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

Neuron 3097 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: 3.2616. Min Range: -3.2616

Max Act: 3.2616. Min Act: -0.0001

Data Index: 1340374 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 3.2616. Min Range: -3.2616

Max Act: 3.1514. Min Act: -0.0001

Data Index: 805766 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 3.2616. Min Range: -3.2616

Max Act: 3.1102. Min Act: -0.0001

Data Index: 887416 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 3.2616. Min Range: -3.2616

Max Act: 2.9170. Min Act: -0.0001

Data Index: 451554 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 3.2616. Min Range: -3.2616

Max Act: 2.8709. Min Act: -0.0001

Data Index: 98339 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 3.2616. Min Range: -3.2616

Max Act: 2.9328. Min Act: -0.0001

Data Index: 760840 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 3.2616. Min Range: -3.2616

Max Act: 3.0461. Min Act: -0.0001

Data Index: 149176 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 3.2616. Min Range: -3.2616

Max Act: 2.7484. Min Act: -0.0001

Data Index: 63702 (C4 (Web Text))

Max Activating Token Index: 413

Text #8

Max Range: 3.2616. Min Range: -3.2616

Max Act: 2.6204. Min Act: -0.0001

Data Index: 8554 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 3.2616. Min Range: -3.2616

Max Act: 2.7184. Min Act: -0.0001

Data Index: 798099 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 3.2616. Min Range: -3.2616

Max Act: 2.6842. Min Act: -0.0001

Data Index: 562059 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 3.2616. Min Range: -3.2616

Max Act: 2.6491. Min Act: -0.0001

Data Index: 161024 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 3.2616. Min Range: -3.2616

Max Act: 2.6615. Min Act: -0.0001

Data Index: 762548 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 3.2616. Min Range: -3.2616

Max Act: 2.6194. Min Act: -0.0001

Data Index: 50757 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 3.2616. Min Range: -3.2616

Max Act: 2.7610. Min Act: -0.0001

Data Index: 404645 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 3.2616. Min Range: -3.2616

Max Act: 2.6103. Min Act: -0.0001

Data Index: 1210685 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 3.2616. Min Range: -3.2616

Max Act: 2.6061. Min Act: -0.0001

Data Index: 1334472 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 3.2616. Min Range: -3.2616

Max Act: 2.4623. Min Act: -0.0001

Data Index: 977011 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 3.2616. Min Range: -3.2616

Max Act: 2.4346. Min Act: -0.0001

Data Index: 503283 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 3.2616. Min Range: -3.2616

Max Act: 2.2647. Min Act: -0.0000

Data Index: 194658 (C4 (Web Text))

Max Activating Token Index: 244