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

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

Neuron 3486 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.3465. Min Act: -0.0002

Data Index: 1341252 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.3418. Min Act: -0.0002

Data Index: 807631 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.3174. Min Act: -0.0002

Data Index: 731411 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.3259. Min Act: -0.0002

Data Index: 2953 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.3147. Min Act: -0.0002

Data Index: 867874 (C4 (Web Text))

Max Activating Token Index: 727

Text #5

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.3091. Min Act: -0.0002

Data Index: 265403 (C4 (Web Text))

Max Activating Token Index: 410

Text #6

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2891. Min Act: -0.0002

Data Index: 1241054 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2863. Min Act: -0.0002

Data Index: 1257233 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.3042. Min Act: -0.0002

Data Index: 173287 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.3017. Min Act: -0.0002

Data Index: 690977 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.3013. Min Act: -0.0002

Data Index: 130879 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2767. Min Act: -0.0002

Data Index: 910276 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2753. Min Act: -0.0002

Data Index: 55924 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2833. Min Act: -0.0002

Data Index: 919647 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2800. Min Act: -0.0002

Data Index: 952428 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2674. Min Act: -0.0002

Data Index: 709355 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2763. Min Act: -0.0002

Data Index: 607686 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2748. Min Act: -0.0002

Data Index: 1333839 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2845. Min Act: -0.0002

Data Index: 1355511 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2641. Min Act: -0.0002

Data Index: 1184259 (C4 (Web Text))

Max Activating Token Index: 410