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

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

Neuron 1078 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.4192. Min Act: -0.0000

Data Index: 289121 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.4073. Min Act: -0.0000

Data Index: 1106690 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.3830. Min Act: -0.0000

Data Index: 883806 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.3303. Min Act: -0.0000

Data Index: 916848 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.2931. Min Act: -0.0000

Data Index: 261356 (C4 (Web Text))

Max Activating Token Index: 357

Text #5

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.2965. Min Act: -0.0000

Data Index: 1066417 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.3041. Min Act: -0.0000

Data Index: 294662 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.2887. Min Act: -0.0000

Data Index: 172680 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.2642. Min Act: -0.0000

Data Index: 1250463 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.2953. Min Act: -0.0000

Data Index: 517162 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.2166. Min Act: -0.0000

Data Index: 694966 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.1561. Min Act: -0.0000

Data Index: 370108 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.1946. Min Act: -0.0000

Data Index: 1265858 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.1857. Min Act: -0.0000

Data Index: 1604507 (Python Code)

Max Activating Token Index: 918

Text #14

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.1756. Min Act: -0.0000

Data Index: 853239 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.1674. Min Act: -0.0000

Data Index: 1310042 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.1740. Min Act: -0.0000

Data Index: 1598019 (Python Code)

Max Activating Token Index: 610

Text #17

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.1518. Min Act: -0.0000

Data Index: 1624051 (Python Code)

Max Activating Token Index: 922

Text #18

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.1510. Min Act: -0.0000

Data Index: 555932 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.1490. Min Act: -0.0000

Data Index: 85653 (C4 (Web Text))

Max Activating Token Index: 355