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

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

Neuron 358 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2147. Min Range: -5.2147

Max Act: 5.2147. Min Act: -0.0000

Data Index: 299230 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 5.2147. Min Range: -5.2147

Max Act: 5.0513. Min Act: -0.0000

Data Index: 1227823 (C4 (Web Text))

Max Activating Token Index: 633

Text #2

Max Range: 5.2147. Min Range: -5.2147

Max Act: 4.7380. Min Act: -0.0000

Data Index: 1346210 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 5.2147. Min Range: -5.2147

Max Act: 4.4902. Min Act: -0.0000

Data Index: 711006 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 5.2147. Min Range: -5.2147

Max Act: 4.0324. Min Act: -0.0000

Data Index: 979409 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 5.2147. Min Range: -5.2147

Max Act: 3.8987. Min Act: -0.0000

Data Index: 810250 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 5.2147. Min Range: -5.2147

Max Act: 3.3944. Min Act: -0.0000

Data Index: 1075692 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 5.2147. Min Range: -5.2147

Max Act: 3.6336. Min Act: -0.0000

Data Index: 729321 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 5.2147. Min Range: -5.2147

Max Act: 3.7695. Min Act: -0.0000

Data Index: 599449 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 5.2147. Min Range: -5.2147

Max Act: 3.8351. Min Act: -0.0000

Data Index: 139695 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 5.2147. Min Range: -5.2147

Max Act: 3.6468. Min Act: -0.0000

Data Index: 827625 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 5.2147. Min Range: -5.2147

Max Act: 3.7699. Min Act: -0.0000

Data Index: 584905 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 5.2147. Min Range: -5.2147

Max Act: 3.4474. Min Act: -0.0000

Data Index: 667552 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 5.2147. Min Range: -5.2147

Max Act: 3.5747. Min Act: -0.0000

Data Index: 335243 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 5.2147. Min Range: -5.2147

Max Act: 4.4524. Min Act: -0.0000

Data Index: 1068742 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 5.2147. Min Range: -5.2147

Max Act: 3.8819. Min Act: -0.0000

Data Index: 1505037 (Python Code)

Max Activating Token Index: 166

Text #16

Max Range: 5.2147. Min Range: -5.2147

Max Act: 3.7104. Min Act: -0.0000

Data Index: 420230 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 5.2147. Min Range: -5.2147

Max Act: 3.7154. Min Act: -0.0000

Data Index: 410960 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 5.2147. Min Range: -5.2147

Max Act: 3.5360. Min Act: -0.0000

Data Index: 1190156 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 5.2147. Min Range: -5.2147

Max Act: 3.6561. Min Act: -0.0000

Data Index: 175419 (C4 (Web Text))

Max Activating Token Index: 462