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

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

Neuron 2510 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.6334. Min Act: -0.0000

Data Index: 886057 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.6469. Min Act: -0.0000

Data Index: 1306386 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.5985. Min Act: -0.0000

Data Index: 547565 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.5504. Min Act: -0.0000

Data Index: 74625 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.5326. Min Act: -0.0000

Data Index: 1308176 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.5649. Min Act: -0.0000

Data Index: 877345 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.5412. Min Act: -0.0000

Data Index: 146691 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.5547. Min Act: -0.0000

Data Index: 1223611 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.5360. Min Act: -0.0000

Data Index: 1262283 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.5285. Min Act: -0.0000

Data Index: 964664 (C4 (Web Text))

Max Activating Token Index: 577

Text #10

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.5163. Min Act: -0.0000

Data Index: 1113511 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.4966. Min Act: -0.0000

Data Index: 1084072 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.5014. Min Act: -0.0000

Data Index: 1095120 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.4973. Min Act: -0.0000

Data Index: 796742 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.4977. Min Act: -0.0000

Data Index: 1355018 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.4706. Min Act: -0.0000

Data Index: 828020 (C4 (Web Text))

Max Activating Token Index: 522

Text #16

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.4512. Min Act: -0.0000

Data Index: 751493 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.4715. Min Act: -0.0000

Data Index: 970097 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.4465. Min Act: -0.0000

Data Index: 72585 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.4307. Min Act: -0.0000

Data Index: 1189552 (C4 (Web Text))

Max Activating Token Index: 794