Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1598 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2323. Min Act: -0.0001

Data Index: 538970 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2094. Min Act: -0.0001

Data Index: 913770 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2259. Min Act: -0.0001

Data Index: 439831 (C4 (Web Text))

Max Activating Token Index: 433

Text #3

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2176. Min Act: -0.0001

Data Index: 844507 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2204. Min Act: -0.0001

Data Index: 1357272 (C4 (Web Text))

Max Activating Token Index: 526

Text #5

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2134. Min Act: -0.0001

Data Index: 491824 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1904. Min Act: -0.0001

Data Index: 917717 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2151. Min Act: -0.0001

Data Index: 1067373 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2004. Min Act: -0.0001

Data Index: 1316685 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2153. Min Act: -0.0001

Data Index: 1113320 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1979. Min Act: -0.0001

Data Index: 1181286 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2137. Min Act: -0.0001

Data Index: 1710 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1978. Min Act: -0.0001

Data Index: 1106555 (C4 (Web Text))

Max Activating Token Index: 958

Text #13

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1852. Min Act: -0.0001

Data Index: 96311 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1900. Min Act: -0.0001

Data Index: 586951 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2046. Min Act: -0.0001

Data Index: 375391 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1989. Min Act: -0.0001

Data Index: 90301 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1886. Min Act: -0.0001

Data Index: 198882 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2016. Min Act: -0.0001

Data Index: 918128 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1952. Min Act: -0.0001

Data Index: 812090 (C4 (Web Text))

Max Activating Token Index: 209