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

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

Neuron 2586 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6969. Min Range: -3.6969

Max Act: 3.6969. Min Act: -0.0001

Data Index: 743764 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 3.6969. Min Range: -3.6969

Max Act: 3.3758. Min Act: -0.0001

Data Index: 638446 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 3.6969. Min Range: -3.6969

Max Act: 2.9892. Min Act: -0.0001

Data Index: 455292 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 3.6969. Min Range: -3.6969

Max Act: 2.6774. Min Act: -0.0001

Data Index: 322919 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 3.6969. Min Range: -3.6969

Max Act: 2.9702. Min Act: -0.0001

Data Index: 961273 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 3.6969. Min Range: -3.6969

Max Act: 2.4949. Min Act: -0.0001

Data Index: 969670 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 3.6969. Min Range: -3.6969

Max Act: 2.7623. Min Act: -0.0001

Data Index: 677616 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 3.6969. Min Range: -3.6969

Max Act: 2.4690. Min Act: -0.0001

Data Index: 88203 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 3.6969. Min Range: -3.6969

Max Act: 2.6751. Min Act: -0.0001

Data Index: 539514 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 3.6969. Min Range: -3.6969

Max Act: 2.5275. Min Act: -0.0001

Data Index: 1168456 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 3.6969. Min Range: -3.6969

Max Act: 2.4928. Min Act: -0.0001

Data Index: 601820 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 3.6969. Min Range: -3.6969

Max Act: 2.3546. Min Act: -0.0001

Data Index: 619143 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 3.6969. Min Range: -3.6969

Max Act: 2.4581. Min Act: -0.0001

Data Index: 215180 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 3.6969. Min Range: -3.6969

Max Act: 2.4134. Min Act: -0.0001

Data Index: 718005 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 3.6969. Min Range: -3.6969

Max Act: 2.3150. Min Act: -0.0001

Data Index: 1280050 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 3.6969. Min Range: -3.6969

Max Act: 2.4079. Min Act: -0.0001

Data Index: 39170 (C4 (Web Text))

Max Activating Token Index: 363

Text #16

Max Range: 3.6969. Min Range: -3.6969

Max Act: 2.5232. Min Act: -0.0001

Data Index: 129880 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 3.6969. Min Range: -3.6969

Max Act: 2.4185. Min Act: -0.0001

Data Index: 986054 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 3.6969. Min Range: -3.6969

Max Act: 2.4033. Min Act: -0.0001

Data Index: 700250 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 3.6969. Min Range: -3.6969

Max Act: 2.2785. Min Act: -0.0001

Data Index: 506169 (C4 (Web Text))

Max Activating Token Index: 91