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

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

Neuron 3486 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: 3.1166. Min Range: -3.1166

Max Act: 3.1166. Min Act: -0.0000

Data Index: 51784 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 3.1166. Min Range: -3.1166

Max Act: 2.9672. Min Act: -0.0000

Data Index: 419391 (C4 (Web Text))

Max Activating Token Index: 682

Text #2

Max Range: 3.1166. Min Range: -3.1166

Max Act: 2.7842. Min Act: -0.0000

Data Index: 1183664 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 3.1166. Min Range: -3.1166

Max Act: 2.9723. Min Act: -0.0001

Data Index: 1310832 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 3.1166. Min Range: -3.1166

Max Act: 2.6181. Min Act: -0.0000

Data Index: 875353 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 3.1166. Min Range: -3.1166

Max Act: 2.8420. Min Act: -0.0000

Data Index: 458434 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 3.1166. Min Range: -3.1166

Max Act: 2.8175. Min Act: -0.0000

Data Index: 534863 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 3.1166. Min Range: -3.1166

Max Act: 2.6795. Min Act: -0.0000

Data Index: 1037224 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 3.1166. Min Range: -3.1166

Max Act: 2.5109. Min Act: -0.0000

Data Index: 188090 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 3.1166. Min Range: -3.1166

Max Act: 2.6237. Min Act: -0.0000

Data Index: 1071121 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 3.1166. Min Range: -3.1166

Max Act: 2.5724. Min Act: -0.0000

Data Index: 1032882 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 3.1166. Min Range: -3.1166

Max Act: 2.4153. Min Act: -0.0000

Data Index: 26556 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 3.1166. Min Range: -3.1166

Max Act: 2.4603. Min Act: -0.0000

Data Index: 822974 (C4 (Web Text))

Max Activating Token Index: 623

Text #13

Max Range: 3.1166. Min Range: -3.1166

Max Act: 2.4517. Min Act: -0.0000

Data Index: 854288 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 3.1166. Min Range: -3.1166

Max Act: 2.4287. Min Act: -0.0000

Data Index: 544693 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 3.1166. Min Range: -3.1166

Max Act: 2.3002. Min Act: -0.0000

Data Index: 893015 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 3.1166. Min Range: -3.1166

Max Act: 2.3948. Min Act: -0.0000

Data Index: 441594 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 3.1166. Min Range: -3.1166

Max Act: 2.4732. Min Act: -0.0000

Data Index: 1246958 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 3.1166. Min Range: -3.1166

Max Act: 2.3247. Min Act: -0.0000

Data Index: 980034 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 3.1166. Min Range: -3.1166

Max Act: 2.2858. Min Act: -0.0000

Data Index: 268107 (C4 (Web Text))

Max Activating Token Index: 582