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

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

Neuron 1765 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.5845. Min Act: -0.0005

Data Index: 1647089 (Python Code)

Max Activating Token Index: 674

Text #1

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.4577. Min Act: -0.0006

Data Index: 556200 (C4 (Web Text))

Max Activating Token Index: 969

Text #2

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.2909. Min Act: -0.0006

Data Index: 1362968 (Python Code)

Max Activating Token Index: 792

Text #3

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.1936. Min Act: -0.0005

Data Index: 1589275 (Python Code)

Max Activating Token Index: 784

Text #4

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.1521. Min Act: -0.0005

Data Index: 1569812 (Python Code)

Max Activating Token Index: 971

Text #5

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.1426. Min Act: -0.0006

Data Index: 1076712 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.1369. Min Act: -0.0006

Data Index: 919090 (C4 (Web Text))

Max Activating Token Index: 952

Text #7

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.1274. Min Act: -0.0005

Data Index: 1592119 (Python Code)

Max Activating Token Index: 645

Text #8

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.1176. Min Act: -0.0005

Data Index: 1385715 (Python Code)

Max Activating Token Index: 205

Text #9

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.1150. Min Act: -0.0005

Data Index: 1612868 (Python Code)

Max Activating Token Index: 895

Text #10

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.1143. Min Act: -0.0005

Data Index: 1212205 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.1024. Min Act: -0.0005

Data Index: 1560403 (Python Code)

Max Activating Token Index: 976

Text #12

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.1105. Min Act: -0.0005

Data Index: 1526546 (Python Code)

Max Activating Token Index: 336

Text #13

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.1040. Min Act: -0.0005

Data Index: 482424 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.0980. Min Act: -0.0005

Data Index: 1573658 (Python Code)

Max Activating Token Index: 944

Text #15

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.0952. Min Act: -0.0005

Data Index: 1507842 (Python Code)

Max Activating Token Index: 603

Text #16

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.0866. Min Act: -0.0005

Data Index: 1421588 (Python Code)

Max Activating Token Index: 818

Text #17

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.0813. Min Act: -0.0005

Data Index: 1561227 (Python Code)

Max Activating Token Index: 311

Text #18

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.0808. Min Act: -0.0006

Data Index: 1486451 (Python Code)

Max Activating Token Index: 359

Text #19

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.0830. Min Act: -0.0005

Data Index: 1375545 (Python Code)

Max Activating Token Index: 640