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

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

Neuron 3194 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2554. Min Range: -1.2554

Max Act: 1.1769. Min Act: -0.0003

Data Index: 296378 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 1.2554. Min Range: -1.2554

Max Act: 1.2554. Min Act: -0.0003

Data Index: 630502 (C4 (Web Text))

Max Activating Token Index: 187

Text #2

Max Range: 1.2554. Min Range: -1.2554

Max Act: 1.0315. Min Act: -0.0003

Data Index: 618335 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 1.2554. Min Range: -1.2554

Max Act: 0.9859. Min Act: -0.0003

Data Index: 1037130 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 1.2554. Min Range: -1.2554

Max Act: 0.9772. Min Act: -0.0003

Data Index: 799119 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 1.2554. Min Range: -1.2554

Max Act: 1.0168. Min Act: -0.0003

Data Index: 103892 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 1.2554. Min Range: -1.2554

Max Act: 0.8871. Min Act: -0.0003

Data Index: 589533 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 1.2554. Min Range: -1.2554

Max Act: 0.9008. Min Act: -0.0003

Data Index: 1174533 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 1.2554. Min Range: -1.2554

Max Act: 0.8614. Min Act: -0.0003

Data Index: 242946 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 1.2554. Min Range: -1.2554

Max Act: 0.7566. Min Act: -0.0003

Data Index: 675303 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 1.2554. Min Range: -1.2554

Max Act: 0.7893. Min Act: -0.0003

Data Index: 405085 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 1.2554. Min Range: -1.2554

Max Act: 0.7264. Min Act: -0.0003

Data Index: 1009140 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 1.2554. Min Range: -1.2554

Max Act: 0.6936. Min Act: -0.0003

Data Index: 939036 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 1.2554. Min Range: -1.2554

Max Act: 0.7392. Min Act: -0.0003

Data Index: 585964 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 1.2554. Min Range: -1.2554

Max Act: 0.7945. Min Act: -0.0003

Data Index: 381772 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 1.2554. Min Range: -1.2554

Max Act: 0.7333. Min Act: -0.0003

Data Index: 853816 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 1.2554. Min Range: -1.2554

Max Act: 0.7470. Min Act: -0.0003

Data Index: 277091 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 1.2554. Min Range: -1.2554

Max Act: 0.6913. Min Act: -0.0003

Data Index: 892144 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 1.2554. Min Range: -1.2554

Max Act: 0.6977. Min Act: -0.0003

Data Index: 305437 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 1.2554. Min Range: -1.2554

Max Act: 0.6515. Min Act: -0.0003

Data Index: 1229868 (C4 (Web Text))

Max Activating Token Index: 407