Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2265 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.4406. Min Act: -0.0001

Data Index: 1045191 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.3883. Min Act: -0.0000

Data Index: 391343 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.2873. Min Act: -0.0001

Data Index: 1050676 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.2380. Min Act: -0.0001

Data Index: 525288 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.2295. Min Act: -0.0001

Data Index: 778265 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.1132. Min Act: -0.0001

Data Index: 635298 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.2210. Min Act: -0.0001

Data Index: 429215 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.1690. Min Act: -0.0001

Data Index: 799511 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.1914. Min Act: -0.0001

Data Index: 1124556 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.1430. Min Act: -0.0001

Data Index: 865116 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.1454. Min Act: -0.0001

Data Index: 913460 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.1045. Min Act: -0.0001

Data Index: 1170157 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.1795. Min Act: -0.0001

Data Index: 740280 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.0938. Min Act: -0.0001

Data Index: 544226 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.0965. Min Act: -0.0001

Data Index: 884583 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.0643. Min Act: -0.0001

Data Index: 1132721 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.0571. Min Act: -0.0001

Data Index: 649723 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.0449. Min Act: -0.0001

Data Index: 693671 (C4 (Web Text))

Max Activating Token Index: 768

Text #18

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.0179. Min Act: -0.0001

Data Index: 1256699 (C4 (Web Text))

Max Activating Token Index: 819

Text #19

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.1764. Min Act: -0.0001

Data Index: 394013 (C4 (Web Text))

Max Activating Token Index: 723