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

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

Neuron 4485 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.8752. Min Act: -0.0000

Data Index: 1281036 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.8421. Min Act: -0.0000

Data Index: 1357887 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.8488. Min Act: -0.0000

Data Index: 45930 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.7636. Min Act: -0.0000

Data Index: 281484 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.7499. Min Act: -0.0000

Data Index: 842067 (C4 (Web Text))

Max Activating Token Index: 409

Text #5

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.6962. Min Act: -0.0000

Data Index: 764785 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.7129. Min Act: -0.0000

Data Index: 378002 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.6882. Min Act: -0.0000

Data Index: 1269984 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.6427. Min Act: -0.0000

Data Index: 1253239 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.5969. Min Act: -0.0000

Data Index: 939134 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.6323. Min Act: -0.0000

Data Index: 85501 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.6316. Min Act: -0.0000

Data Index: 139255 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.6557. Min Act: -0.0000

Data Index: 180040 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.5985. Min Act: -0.0000

Data Index: 657015 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.6343. Min Act: -0.0000

Data Index: 194082 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.5929. Min Act: -0.0000

Data Index: 1341138 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.5565. Min Act: -0.0000

Data Index: 227775 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.5395. Min Act: -0.0000

Data Index: 1259318 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.5787. Min Act: -0.0000

Data Index: 1049578 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.5750. Min Act: -0.0000

Data Index: 866280 (C4 (Web Text))

Max Activating Token Index: 257