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

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

Neuron 2307 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5757. Min Range: -1.5757

Max Act: 1.5757. Min Act: -0.0001

Data Index: 1047570 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 1.5757. Min Range: -1.5757

Max Act: 0.9455. Min Act: -0.0001

Data Index: 1105456 (C4 (Web Text))

Max Activating Token Index: 238

Text #2

Max Range: 1.5757. Min Range: -1.5757

Max Act: 0.9616. Min Act: -0.0001

Data Index: 1306934 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 1.5757. Min Range: -1.5757

Max Act: 0.7989. Min Act: -0.0001

Data Index: 1262496 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 1.5757. Min Range: -1.5757

Max Act: 0.8003. Min Act: -0.0001

Data Index: 1133697 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 1.5757. Min Range: -1.5757

Max Act: 0.8128. Min Act: -0.0001

Data Index: 106658 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 1.5757. Min Range: -1.5757

Max Act: 0.7811. Min Act: -0.0001

Data Index: 1263440 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 1.5757. Min Range: -1.5757

Max Act: 0.7896. Min Act: -0.0001

Data Index: 812259 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 1.5757. Min Range: -1.5757

Max Act: 0.7316. Min Act: -0.0001

Data Index: 1165042 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 1.5757. Min Range: -1.5757

Max Act: 0.7590. Min Act: -0.0001

Data Index: 1095151 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 1.5757. Min Range: -1.5757

Max Act: 0.7685. Min Act: -0.0001

Data Index: 247100 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 1.5757. Min Range: -1.5757

Max Act: 0.6521. Min Act: -0.0001

Data Index: 343316 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 1.5757. Min Range: -1.5757

Max Act: 0.7777. Min Act: -0.0001

Data Index: 165638 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 1.5757. Min Range: -1.5757

Max Act: 0.7330. Min Act: -0.0001

Data Index: 1193647 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 1.5757. Min Range: -1.5757

Max Act: 0.7481. Min Act: -0.0001

Data Index: 1194689 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 1.5757. Min Range: -1.5757

Max Act: 0.7009. Min Act: -0.0001

Data Index: 1281236 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 1.5757. Min Range: -1.5757

Max Act: 0.6755. Min Act: -0.0001

Data Index: 100602 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 1.5757. Min Range: -1.5757

Max Act: 0.6948. Min Act: -0.0001

Data Index: 626749 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 1.5757. Min Range: -1.5757

Max Act: 0.7162. Min Act: -0.0001

Data Index: 579495 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 1.5757. Min Range: -1.5757

Max Act: 0.6665. Min Act: -0.0001

Data Index: 80682 (C4 (Web Text))

Max Activating Token Index: 310