Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4666 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1869. Min Range: -2.1869

Max Act: 2.1869. Min Act: -0.0001

Data Index: 345109 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 2.1869. Min Range: -2.1869

Max Act: 1.6411. Min Act: -0.0001

Data Index: 248670 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 2.1869. Min Range: -2.1869

Max Act: 1.7603. Min Act: -0.0000

Data Index: 420143 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 2.1869. Min Range: -2.1869

Max Act: 1.6234. Min Act: -0.0000

Data Index: 694562 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 2.1869. Min Range: -2.1869

Max Act: 1.6178. Min Act: -0.0001

Data Index: 207965 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 2.1869. Min Range: -2.1869

Max Act: 1.4469. Min Act: -0.0000

Data Index: 698762 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 2.1869. Min Range: -2.1869

Max Act: 1.4186. Min Act: -0.0000

Data Index: 331623 (C4 (Web Text))

Max Activating Token Index: 506

Text #7

Max Range: 2.1869. Min Range: -2.1869

Max Act: 1.4994. Min Act: -0.0000

Data Index: 35386 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 2.1869. Min Range: -2.1869

Max Act: 1.4933. Min Act: -0.0000

Data Index: 223016 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 2.1869. Min Range: -2.1869

Max Act: 1.4732. Min Act: -0.0000

Data Index: 1053124 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 2.1869. Min Range: -2.1869

Max Act: 1.3391. Min Act: -0.0001

Data Index: 544681 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 2.1869. Min Range: -2.1869

Max Act: 1.3351. Min Act: -0.0000

Data Index: 1001801 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 2.1869. Min Range: -2.1869

Max Act: 1.3174. Min Act: -0.0000

Data Index: 833604 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 2.1869. Min Range: -2.1869

Max Act: 1.4741. Min Act: -0.0000

Data Index: 1013203 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 2.1869. Min Range: -2.1869

Max Act: 1.3857. Min Act: -0.0000

Data Index: 1240904 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 2.1869. Min Range: -2.1869

Max Act: 1.3775. Min Act: -0.0000

Data Index: 438188 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 2.1869. Min Range: -2.1869

Max Act: 1.3634. Min Act: -0.0001

Data Index: 133454 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 2.1869. Min Range: -2.1869

Max Act: 1.3544. Min Act: -0.0000

Data Index: 521566 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 2.1869. Min Range: -2.1869

Max Act: 1.2745. Min Act: -0.0001

Data Index: 964138 (C4 (Web Text))

Max Activating Token Index: 553

Text #19

Max Range: 2.1869. Min Range: -2.1869

Max Act: 1.2883. Min Act: -0.0001

Data Index: 185613 (C4 (Web Text))

Max Activating Token Index: 164