Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 446 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.9540. Min Act: -0.0001

Data Index: 352672 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.8556. Min Act: -0.0001

Data Index: 1047018 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.9518. Min Act: -0.0001

Data Index: 950279 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.6429. Min Act: -0.0001

Data Index: 979756 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.6433. Min Act: -0.0001

Data Index: 1339358 (C4 (Web Text))

Max Activating Token Index: 196

Text #5

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.6787. Min Act: -0.0001

Data Index: 8643 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.6357. Min Act: -0.0001

Data Index: 894538 (C4 (Web Text))

Max Activating Token Index: 691

Text #7

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.5287. Min Act: -0.0001

Data Index: 93750 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.6020. Min Act: -0.0001

Data Index: 865604 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.6476. Min Act: -0.0001

Data Index: 692876 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.6229. Min Act: -0.0001

Data Index: 867656 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.5539. Min Act: -0.0001

Data Index: 551173 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.7180. Min Act: -0.0001

Data Index: 190337 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.5594. Min Act: -0.0001

Data Index: 1052111 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.5110. Min Act: -0.0001

Data Index: 371458 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.5529. Min Act: -0.0001

Data Index: 1169852 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.5500. Min Act: -0.0001

Data Index: 336628 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.5055. Min Act: -0.0001

Data Index: 605991 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.4487. Min Act: -0.0001

Data Index: 520688 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 1.9540. Min Range: -1.9540

Max Act: 1.5301. Min Act: -0.0001

Data Index: 1035881 (C4 (Web Text))

Max Activating Token Index: 396