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

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

Neuron 4204 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: 1.8318. Min Range: -1.8318

Max Act: 1.8318. Min Act: -0.0001

Data Index: 1073825 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.5566. Min Act: -0.0001

Data Index: 1085420 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.7583. Min Act: -0.0001

Data Index: 218174 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.7020. Min Act: -0.0001

Data Index: 1060678 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.7370. Min Act: -0.0001

Data Index: 585147 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.6459. Min Act: -0.0001

Data Index: 1319053 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.3741. Min Act: -0.0001

Data Index: 506435 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.5633. Min Act: -0.0001

Data Index: 623947 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.4867. Min Act: -0.0001

Data Index: 1038349 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.3201. Min Act: -0.0001

Data Index: 1292170 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.4382. Min Act: -0.0001

Data Index: 1194973 (C4 (Web Text))

Max Activating Token Index: 606

Text #11

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.4398. Min Act: -0.0001

Data Index: 1291668 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.3162. Min Act: -0.0001

Data Index: 459887 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.3550. Min Act: -0.0001

Data Index: 979423 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.1982. Min Act: -0.0001

Data Index: 328249 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.3002. Min Act: -0.0001

Data Index: 918747 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.2960. Min Act: -0.0001

Data Index: 328692 (C4 (Web Text))

Max Activating Token Index: 830

Text #17

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.3147. Min Act: -0.0001

Data Index: 244898 (C4 (Web Text))

Max Activating Token Index: 3

Text #18

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.2919. Min Act: -0.0001

Data Index: 1085991 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.2521. Min Act: -0.0001

Data Index: 84979 (C4 (Web Text))

Max Activating Token Index: 13