Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 898 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1195. Min Act: -0.0003

Data Index: 702495 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1193. Min Act: -0.0003

Data Index: 1552174 (Python Code)

Max Activating Token Index: 977

Text #2

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1160. Min Act: -0.0003

Data Index: 1392255 (Python Code)

Max Activating Token Index: 1009

Text #3

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1009. Min Act: -0.0003

Data Index: 120670 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0995. Min Act: -0.0003

Data Index: 237267 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1005. Min Act: -0.0003

Data Index: 1096846 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1000. Min Act: -0.0003

Data Index: 599677 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0943. Min Act: -0.0003

Data Index: 1273489 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1012. Min Act: -0.0003

Data Index: 706579 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0955. Min Act: -0.0003

Data Index: 911965 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0918. Min Act: -0.0003

Data Index: 1340830 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0935. Min Act: -0.0003

Data Index: 876745 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0943. Min Act: -0.0003

Data Index: 468979 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0921. Min Act: -0.0003

Data Index: 1534123 (Python Code)

Max Activating Token Index: 921

Text #14

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0892. Min Act: -0.0003

Data Index: 738178 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0898. Min Act: -0.0003

Data Index: 523763 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0931. Min Act: -0.0003

Data Index: 409262 (C4 (Web Text))

Max Activating Token Index: 450

Text #17

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0922. Min Act: -0.0003

Data Index: 72022 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0875. Min Act: -0.0004

Data Index: 1335851 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0892. Min Act: -0.0003

Data Index: 1041430 (C4 (Web Text))

Max Activating Token Index: 884