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

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

Neuron 3373 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: 1.2901. Min Range: -1.2901

Max Act: 1.2811. Min Act: -0.0001

Data Index: 1229068 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 1.2901. Min Range: -1.2901

Max Act: 1.2901. Min Act: -0.0001

Data Index: 898377 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 1.2901. Min Range: -1.2901

Max Act: 1.2078. Min Act: -0.0001

Data Index: 278238 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 1.2901. Min Range: -1.2901

Max Act: 1.1200. Min Act: -0.0001

Data Index: 961220 (C4 (Web Text))

Max Activating Token Index: 607

Text #4

Max Range: 1.2901. Min Range: -1.2901

Max Act: 1.1413. Min Act: -0.0001

Data Index: 1015870 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 1.2901. Min Range: -1.2901

Max Act: 1.1352. Min Act: -0.0001

Data Index: 668685 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 1.2901. Min Range: -1.2901

Max Act: 1.1300. Min Act: -0.0001

Data Index: 1172752 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 1.2901. Min Range: -1.2901

Max Act: 1.1161. Min Act: -0.0001

Data Index: 1139555 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 1.2901. Min Range: -1.2901

Max Act: 1.0712. Min Act: -0.0001

Data Index: 697046 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 1.2901. Min Range: -1.2901

Max Act: 1.0805. Min Act: -0.0001

Data Index: 1150052 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 1.2901. Min Range: -1.2901

Max Act: 1.1560. Min Act: -0.0001

Data Index: 885190 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 1.2901. Min Range: -1.2901

Max Act: 1.0469. Min Act: -0.0001

Data Index: 390490 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 1.2901. Min Range: -1.2901

Max Act: 1.0944. Min Act: -0.0001

Data Index: 195427 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 1.2901. Min Range: -1.2901

Max Act: 1.0599. Min Act: -0.0001

Data Index: 27148 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 1.2901. Min Range: -1.2901

Max Act: 1.0612. Min Act: -0.0001

Data Index: 1138716 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 1.2901. Min Range: -1.2901

Max Act: 1.0623. Min Act: -0.0001

Data Index: 1036227 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 1.2901. Min Range: -1.2901

Max Act: 1.0081. Min Act: -0.0001

Data Index: 935096 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 1.2901. Min Range: -1.2901

Max Act: 1.0034. Min Act: -0.0001

Data Index: 1064055 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 1.2901. Min Range: -1.2901

Max Act: 1.0679. Min Act: -0.0001

Data Index: 765481 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 1.2901. Min Range: -1.2901

Max Act: 1.1031. Min Act: -0.0001

Data Index: 230107 (C4 (Web Text))

Max Activating Token Index: 759