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

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

Neuron 65 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: 1.1863. Min Range: -1.1863

Max Act: 1.1863. Min Act: -0.0001

Data Index: 1303434 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 1.1863. Min Range: -1.1863

Max Act: 1.1699. Min Act: -0.0001

Data Index: 116140 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 1.1863. Min Range: -1.1863

Max Act: 1.1147. Min Act: -0.0001

Data Index: 806776 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 1.1863. Min Range: -1.1863

Max Act: 1.1051. Min Act: -0.0001

Data Index: 1105738 (C4 (Web Text))

Max Activating Token Index: 354

Text #4

Max Range: 1.1863. Min Range: -1.1863

Max Act: 1.0908. Min Act: -0.0001

Data Index: 673653 (C4 (Web Text))

Max Activating Token Index: 397

Text #5

Max Range: 1.1863. Min Range: -1.1863

Max Act: 1.0316. Min Act: -0.0001

Data Index: 1173331 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 1.1863. Min Range: -1.1863

Max Act: 1.0233. Min Act: -0.0001

Data Index: 111784 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 1.1863. Min Range: -1.1863

Max Act: 1.0519. Min Act: -0.0001

Data Index: 1040795 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 1.1863. Min Range: -1.1863

Max Act: 1.0526. Min Act: -0.0001

Data Index: 720584 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 1.1863. Min Range: -1.1863

Max Act: 1.0157. Min Act: -0.0001

Data Index: 1203215 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 1.1863. Min Range: -1.1863

Max Act: 1.0465. Min Act: -0.0001

Data Index: 568813 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 1.1863. Min Range: -1.1863

Max Act: 1.0023. Min Act: -0.0001

Data Index: 488233 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 1.1863. Min Range: -1.1863

Max Act: 1.0596. Min Act: -0.0001

Data Index: 112021 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 1.1863. Min Range: -1.1863

Max Act: 1.0811. Min Act: -0.0001

Data Index: 587562 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 1.1863. Min Range: -1.1863

Max Act: 1.0175. Min Act: -0.0001

Data Index: 1083302 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 1.1863. Min Range: -1.1863

Max Act: 0.9795. Min Act: -0.0001

Data Index: 219160 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 1.1863. Min Range: -1.1863

Max Act: 1.0348. Min Act: -0.0001

Data Index: 1218608 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 1.1863. Min Range: -1.1863

Max Act: 1.0027. Min Act: -0.0001

Data Index: 1479766 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 1.1863. Min Range: -1.1863

Max Act: 1.0019. Min Act: -0.0001

Data Index: 73413 (C4 (Web Text))

Max Activating Token Index: 821

Text #19

Max Range: 1.1863. Min Range: -1.1863

Max Act: 1.0386. Min Act: -0.0001

Data Index: 337664 (C4 (Web Text))

Max Activating Token Index: 788