Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1909 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0194. Min Range: -1.0194

Max Act: 1.0194. Min Act: -0.0000

Data Index: 795563 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.9008. Min Act: 0.0000

Data Index: 67771 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.9082. Min Act: 0.0000

Data Index: 279909 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.9106. Min Act: -0.0000

Data Index: 653987 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.8923. Min Act: -0.0000

Data Index: 705068 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.8261. Min Act: -0.0000

Data Index: 427671 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.8627. Min Act: -0.0000

Data Index: 170134 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.8491. Min Act: -0.0000

Data Index: 286063 (C4 (Web Text))

Max Activating Token Index: 884

Text #8

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.8426. Min Act: -0.0000

Data Index: 1303747 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.8454. Min Act: -0.0000

Data Index: 271418 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.7459. Min Act: -0.0000

Data Index: 512544 (C4 (Web Text))

Max Activating Token Index: 385

Text #11

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.8207. Min Act: -0.0000

Data Index: 547322 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.7638. Min Act: -0.0000

Data Index: 423775 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.8227. Min Act: -0.0000

Data Index: 4707 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.8044. Min Act: -0.0000

Data Index: 479028 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.7538. Min Act: -0.0000

Data Index: 1337262 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.7967. Min Act: -0.0000

Data Index: 68709 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.7659. Min Act: -0.0000

Data Index: 109391 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.7697. Min Act: -0.0000

Data Index: 1049408 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.7705. Min Act: -0.0000

Data Index: 1010900 (C4 (Web Text))

Max Activating Token Index: 939