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

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

Neuron 289 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.5952. Min Act: -0.0000

Data Index: 760689 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.3093. Min Act: -0.0000

Data Index: 522017 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.1570. Min Act: -0.0000

Data Index: 518246 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 3.5952. Min Range: -3.5952

Max Act: 2.9569. Min Act: -0.0000

Data Index: 4707 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.0546. Min Act: -0.0000

Data Index: 1106345 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.2137. Min Act: -0.0000

Data Index: 771382 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 3.5952. Min Range: -3.5952

Max Act: 2.9965. Min Act: -0.0000

Data Index: 1158316 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.1466. Min Act: -0.0000

Data Index: 79158 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.1388. Min Act: -0.0000

Data Index: 229678 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.0963. Min Act: -0.0000

Data Index: 37195 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 3.5952. Min Range: -3.5952

Max Act: 2.9300. Min Act: -0.0000

Data Index: 680804 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 3.5952. Min Range: -3.5952

Max Act: 2.8695. Min Act: -0.0000

Data Index: 468451 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 3.5952. Min Range: -3.5952

Max Act: 2.9906. Min Act: -0.0000

Data Index: 511047 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 3.5952. Min Range: -3.5952

Max Act: 2.9587. Min Act: -0.0000

Data Index: 635117 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 3.5952. Min Range: -3.5952

Max Act: 2.9461. Min Act: -0.0000

Data Index: 241649 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 3.5952. Min Range: -3.5952

Max Act: 2.9335. Min Act: -0.0000

Data Index: 561148 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 3.5952. Min Range: -3.5952

Max Act: 2.9122. Min Act: -0.0000

Data Index: 17848 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 3.5952. Min Range: -3.5952

Max Act: 2.8004. Min Act: -0.0000

Data Index: 1282581 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 3.5952. Min Range: -3.5952

Max Act: 2.7558. Min Act: -0.0000

Data Index: 511564 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.0324. Min Act: -0.0000

Data Index: 1345482 (C4 (Web Text))

Max Activating Token Index: 523