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

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

Neuron 2027 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.9119. Min Act: -0.0000

Data Index: 1114211 (C4 (Web Text))

Max Activating Token Index: 493

Text #1

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.6054. Min Act: -0.0000

Data Index: 14194 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.5815. Min Act: -0.0000

Data Index: 335221 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.3990. Min Act: -0.0000

Data Index: 506005 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.3138. Min Act: -0.0000

Data Index: 505595 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.2043. Min Act: -0.0000

Data Index: 137101 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.2763. Min Act: -0.0000

Data Index: 925049 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.1477. Min Act: -0.0000

Data Index: 573286 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.1036. Min Act: -0.0000

Data Index: 1225272 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.2231. Min Act: -0.0000

Data Index: 1142781 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.1108. Min Act: -0.0000

Data Index: 1406932 (Python Code)

Max Activating Token Index: 268

Text #11

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.0887. Min Act: -0.0000

Data Index: 1321656 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.2031. Min Act: -0.0000

Data Index: 137115 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.1607. Min Act: -0.0000

Data Index: 623438 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.2653. Min Act: -0.0000

Data Index: 767091 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.1543. Min Act: -0.0000

Data Index: 1115662 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.1318. Min Act: -0.0000

Data Index: 372979 (C4 (Web Text))

Max Activating Token Index: 963

Text #17

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.0156. Min Act: -0.0000

Data Index: 461628 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 2.9119. Min Range: -2.9119

Max Act: 1.3314. Min Act: -0.0000

Data Index: 1587329 (Python Code)

Max Activating Token Index: 635

Text #19

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.2196. Min Act: -0.0000

Data Index: 595603 (C4 (Web Text))

Max Activating Token Index: 119