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

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

Neuron 516 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.7575. Min Act: -0.0005

Data Index: 27878 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.6931. Min Act: -0.0005

Data Index: 47759 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.7430. Min Act: -0.0005

Data Index: 418503 (C4 (Web Text))

Max Activating Token Index: 517

Text #3

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.6651. Min Act: -0.0005

Data Index: 867236 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.5985. Min Act: -0.0005

Data Index: 327855 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.6452. Min Act: -0.0005

Data Index: 1074903 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.6855. Min Act: -0.0005

Data Index: 262319 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.6909. Min Act: -0.0005

Data Index: 585002 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.6954. Min Act: -0.0005

Data Index: 920314 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.6093. Min Act: -0.0005

Data Index: 1220091 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.6730. Min Act: -0.0005

Data Index: 416751 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.6294. Min Act: -0.0005

Data Index: 33224 (C4 (Web Text))

Max Activating Token Index: 259

Text #12

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.6248. Min Act: -0.0005

Data Index: 496661 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.6381. Min Act: -0.0005

Data Index: 1132775 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.6052. Min Act: -0.0005

Data Index: 998925 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.6221. Min Act: -0.0005

Data Index: 1298509 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.6219. Min Act: -0.0005

Data Index: 797316 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.6312. Min Act: -0.0005

Data Index: 1185691 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.6157. Min Act: -0.0005

Data Index: 1325173 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.5721. Min Act: -0.0005

Data Index: 358346 (C4 (Web Text))

Max Activating Token Index: 958