Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1741 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4567. Min Range: -1.4567

Max Act: 1.4567. Min Act: -0.0001

Data Index: 1024322 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 1.4567. Min Range: -1.4567

Max Act: 1.1658. Min Act: -0.0001

Data Index: 686360 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 1.4567. Min Range: -1.4567

Max Act: 1.2234. Min Act: -0.0001

Data Index: 1005203 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 1.4567. Min Range: -1.4567

Max Act: 1.1322. Min Act: -0.0001

Data Index: 965774 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 1.4567. Min Range: -1.4567

Max Act: 1.0746. Min Act: -0.0001

Data Index: 1123580 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 1.4567. Min Range: -1.4567

Max Act: 1.0609. Min Act: -0.0001

Data Index: 1198351 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 1.4567. Min Range: -1.4567

Max Act: 1.0086. Min Act: -0.0001

Data Index: 1084148 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 1.4567. Min Range: -1.4567

Max Act: 1.0651. Min Act: -0.0001

Data Index: 788222 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 1.4567. Min Range: -1.4567

Max Act: 1.0697. Min Act: -0.0001

Data Index: 709213 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 1.4567. Min Range: -1.4567

Max Act: 1.0106. Min Act: -0.0001

Data Index: 1233591 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 1.4567. Min Range: -1.4567

Max Act: 0.9760. Min Act: -0.0001

Data Index: 1149673 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 1.4567. Min Range: -1.4567

Max Act: 1.0069. Min Act: -0.0001

Data Index: 699963 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 1.4567. Min Range: -1.4567

Max Act: 1.0306. Min Act: -0.0001

Data Index: 165256 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 1.4567. Min Range: -1.4567

Max Act: 1.0745. Min Act: -0.0001

Data Index: 935918 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 1.4567. Min Range: -1.4567

Max Act: 0.9891. Min Act: -0.0001

Data Index: 85575 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 1.4567. Min Range: -1.4567

Max Act: 0.9589. Min Act: -0.0001

Data Index: 292343 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 1.4567. Min Range: -1.4567

Max Act: 0.9151. Min Act: -0.0001

Data Index: 780000 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 1.4567. Min Range: -1.4567

Max Act: 0.9138. Min Act: -0.0001

Data Index: 344851 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 1.4567. Min Range: -1.4567

Max Act: 0.9126. Min Act: -0.0001

Data Index: 1098931 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 1.4567. Min Range: -1.4567

Max Act: 0.9427. Min Act: -0.0001

Data Index: 552357 (C4 (Web Text))

Max Activating Token Index: 10