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

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

Neuron 4520 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.8324. Min Act: -0.0001

Data Index: 763210 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.6941. Min Act: -0.0001

Data Index: 1112782 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.5467. Min Act: -0.0001

Data Index: 1265374 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.5796. Min Act: -0.0001

Data Index: 734572 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.6135. Min Act: -0.0001

Data Index: 2676 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.5680. Min Act: -0.0001

Data Index: 768 (C4 (Web Text))

Max Activating Token Index: 356

Text #6

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.5511. Min Act: -0.0001

Data Index: 1319704 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.5135. Min Act: -0.0001

Data Index: 506627 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.4882. Min Act: -0.0001

Data Index: 427833 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.5595. Min Act: -0.0001

Data Index: 840742 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.7096. Min Act: -0.0001

Data Index: 854543 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.5739. Min Act: -0.0001

Data Index: 1001174 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.4048. Min Act: -0.0001

Data Index: 913138 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.5349. Min Act: -0.0001

Data Index: 129192 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.4459. Min Act: -0.0001

Data Index: 856933 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.3765. Min Act: -0.0001

Data Index: 1116818 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.5904. Min Act: -0.0001

Data Index: 75930 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.5262. Min Act: -0.0001

Data Index: 25985 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.5280. Min Act: -0.0001

Data Index: 97245 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.5245. Min Act: -0.0001

Data Index: 221934 (C4 (Web Text))

Max Activating Token Index: 28