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

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

Neuron 1415 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5104. Min Range: -1.5104

Max Act: 1.5104. Min Act: -0.0002

Data Index: 700112 (C4 (Web Text))

Max Activating Token Index: 798

Text #1

Max Range: 1.5104. Min Range: -1.5104

Max Act: 1.4753. Min Act: -0.0002

Data Index: 698231 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 1.5104. Min Range: -1.5104

Max Act: 1.3712. Min Act: -0.0002

Data Index: 355411 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 1.5104. Min Range: -1.5104

Max Act: 1.3095. Min Act: -0.0002

Data Index: 128762 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 1.5104. Min Range: -1.5104

Max Act: 1.2672. Min Act: -0.0002

Data Index: 327254 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 1.5104. Min Range: -1.5104

Max Act: 1.2609. Min Act: -0.0002

Data Index: 1304552 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 1.5104. Min Range: -1.5104

Max Act: 1.2258. Min Act: -0.0002

Data Index: 191245 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 1.5104. Min Range: -1.5104

Max Act: 1.2626. Min Act: -0.0002

Data Index: 268514 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 1.5104. Min Range: -1.5104

Max Act: 1.1864. Min Act: -0.0002

Data Index: 842423 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 1.5104. Min Range: -1.5104

Max Act: 1.2118. Min Act: -0.0003

Data Index: 1157252 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 1.5104. Min Range: -1.5104

Max Act: 1.0928. Min Act: -0.0002

Data Index: 649445 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 1.5104. Min Range: -1.5104

Max Act: 1.1059. Min Act: -0.0002

Data Index: 395520 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 1.5104. Min Range: -1.5104

Max Act: 1.1277. Min Act: -0.0002

Data Index: 1106494 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 1.5104. Min Range: -1.5104

Max Act: 1.2493. Min Act: -0.0002

Data Index: 311352 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 1.5104. Min Range: -1.5104

Max Act: 0.9701. Min Act: -0.0002

Data Index: 1217917 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 1.5104. Min Range: -1.5104

Max Act: 1.0039. Min Act: -0.0002

Data Index: 277408 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 1.5104. Min Range: -1.5104

Max Act: 1.0414. Min Act: -0.0002

Data Index: 301471 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 1.5104. Min Range: -1.5104

Max Act: 0.9864. Min Act: -0.0002

Data Index: 232126 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 1.5104. Min Range: -1.5104

Max Act: 1.0302. Min Act: -0.0002

Data Index: 1270861 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 1.5104. Min Range: -1.5104

Max Act: 0.9741. Min Act: -0.0002

Data Index: 1057499 (C4 (Web Text))

Max Activating Token Index: 369