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

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

Neuron 4429 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: 1.5019. Min Range: -1.5019

Max Act: 1.4985. Min Act: -0.0000

Data Index: 1421069 (Python Code)

Max Activating Token Index: 866

Text #1

Max Range: 1.5019. Min Range: -1.5019

Max Act: 1.5019. Min Act: -0.0000

Data Index: 1198984 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 1.5019. Min Range: -1.5019

Max Act: 1.4081. Min Act: -0.0000

Data Index: 592972 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 1.5019. Min Range: -1.5019

Max Act: 1.3445. Min Act: -0.0000

Data Index: 1209749 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 1.5019. Min Range: -1.5019

Max Act: 1.3334. Min Act: -0.0000

Data Index: 1541067 (Python Code)

Max Activating Token Index: 510

Text #5

Max Range: 1.5019. Min Range: -1.5019

Max Act: 1.2714. Min Act: -0.0000

Data Index: 936165 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 1.5019. Min Range: -1.5019

Max Act: 1.2605. Min Act: -0.0000

Data Index: 397007 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 1.5019. Min Range: -1.5019

Max Act: 1.2679. Min Act: -0.0000

Data Index: 1654475 (Python Code)

Max Activating Token Index: 578

Text #8

Max Range: 1.5019. Min Range: -1.5019

Max Act: 1.2428. Min Act: -0.0001

Data Index: 1376396 (Python Code)

Max Activating Token Index: 455

Text #9

Max Range: 1.5019. Min Range: -1.5019

Max Act: 1.2644. Min Act: -0.0000

Data Index: 1399229 (Python Code)

Max Activating Token Index: 941

Text #10

Max Range: 1.5019. Min Range: -1.5019

Max Act: 1.2466. Min Act: -0.0000

Data Index: 1649911 (Python Code)

Max Activating Token Index: 317

Text #11

Max Range: 1.5019. Min Range: -1.5019

Max Act: 1.2832. Min Act: -0.0000

Data Index: 1353895 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 1.5019. Min Range: -1.5019

Max Act: 1.2383. Min Act: -0.0000

Data Index: 854480 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 1.5019. Min Range: -1.5019

Max Act: 1.1645. Min Act: -0.0000

Data Index: 1186488 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 1.5019. Min Range: -1.5019

Max Act: 1.1549. Min Act: -0.0000

Data Index: 574731 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 1.5019. Min Range: -1.5019

Max Act: 1.1223. Min Act: -0.0000

Data Index: 1280258 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 1.5019. Min Range: -1.5019

Max Act: 1.2123. Min Act: -0.0000

Data Index: 1643976 (Python Code)

Max Activating Token Index: 575

Text #17

Max Range: 1.5019. Min Range: -1.5019

Max Act: 1.1746. Min Act: -0.0000

Data Index: 1515992 (Python Code)

Max Activating Token Index: 846

Text #18

Max Range: 1.5019. Min Range: -1.5019

Max Act: 1.1740. Min Act: -0.0000

Data Index: 25638 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 1.5019. Min Range: -1.5019

Max Act: 1.1740. Min Act: -0.0000

Data Index: 1530387 (Python Code)

Max Activating Token Index: 585