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

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

Neuron 212 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.7318. Min Act: -0.0000

Data Index: 1156499 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.2988. Min Act: -0.0000

Data Index: 269340 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.3768. Min Act: -0.0000

Data Index: 1194718 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.3514. Min Act: -0.0000

Data Index: 1203048 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.2726. Min Act: -0.0000

Data Index: 1008399 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.2701. Min Act: -0.0000

Data Index: 834462 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.3243. Min Act: -0.0000

Data Index: 622240 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.2774. Min Act: -0.0000

Data Index: 931708 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.3423. Min Act: -0.0000

Data Index: 1038480 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.3326. Min Act: -0.0000

Data Index: 1117579 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.1789. Min Act: -0.0001

Data Index: 542072 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.2783. Min Act: -0.0000

Data Index: 1211455 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.3255. Min Act: -0.0000

Data Index: 367249 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.2049. Min Act: -0.0001

Data Index: 1143095 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.2745. Min Act: -0.0000

Data Index: 299784 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.1923. Min Act: -0.0000

Data Index: 1155789 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.1944. Min Act: -0.0000

Data Index: 77343 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.2574. Min Act: -0.0000

Data Index: 761316 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.2090. Min Act: -0.0000

Data Index: 1003285 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.2334. Min Act: -0.0000

Data Index: 748469 (C4 (Web Text))

Max Activating Token Index: 186