Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1851 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1274089 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0641. Min Act: -0.0002

Data Index: 167313 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0603. Min Act: -0.0002

Data Index: 551664 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0593. Min Act: -0.0004

Data Index: 932908 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0567. Min Act: -0.0002

Data Index: 354320 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0527. Min Act: -0.0003

Data Index: 1183923 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0551. Min Act: -0.0003

Data Index: 887208 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0530. Min Act: -0.0003

Data Index: 602770 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0543. Min Act: -0.0002

Data Index: 776211 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0515. Min Act: -0.0003

Data Index: 524918 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1304501 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0506. Min Act: -0.0003

Data Index: 196809 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0501. Min Act: -0.0003

Data Index: 249304 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0497. Min Act: -0.0002

Data Index: 65436 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0492. Min Act: -0.0002

Data Index: 917534 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0479. Min Act: -0.0003

Data Index: 490240 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0484. Min Act: -0.0001

Data Index: 323486 (C4 (Web Text))

Max Activating Token Index: 325

Text #17

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0468. Min Act: -0.0002

Data Index: 1200244 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0483. Min Act: -0.0003

Data Index: 187411 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0475. Min Act: -0.0002

Data Index: 773794 (C4 (Web Text))

Max Activating Token Index: 140