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

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

Neuron 2548 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: 1.5202. Min Range: -1.5202

Max Act: 1.5202. Min Act: -0.0000

Data Index: 238481 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 1.5202. Min Range: -1.5202

Max Act: 1.4217. Min Act: -0.0000

Data Index: 379338 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 1.5202. Min Range: -1.5202

Max Act: 1.4217. Min Act: -0.0000

Data Index: 349216 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 1.5202. Min Range: -1.5202

Max Act: 1.3832. Min Act: -0.0000

Data Index: 1246559 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 1.5202. Min Range: -1.5202

Max Act: 1.3808. Min Act: -0.0000

Data Index: 1209219 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 1.5202. Min Range: -1.5202

Max Act: 1.3317. Min Act: -0.0000

Data Index: 972644 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 1.5202. Min Range: -1.5202

Max Act: 1.2966. Min Act: -0.0000

Data Index: 709359 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 1.5202. Min Range: -1.5202

Max Act: 1.2936. Min Act: -0.0000

Data Index: 153253 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 1.5202. Min Range: -1.5202

Max Act: 1.2136. Min Act: -0.0000

Data Index: 158873 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 1.5202. Min Range: -1.5202

Max Act: 1.1968. Min Act: -0.0000

Data Index: 1110515 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 1.5202. Min Range: -1.5202

Max Act: 1.2771. Min Act: -0.0000

Data Index: 1160557 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 1.5202. Min Range: -1.5202

Max Act: 1.2586. Min Act: -0.0000

Data Index: 97139 (C4 (Web Text))

Max Activating Token Index: 618

Text #12

Max Range: 1.5202. Min Range: -1.5202

Max Act: 1.2661. Min Act: -0.0000

Data Index: 676749 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 1.5202. Min Range: -1.5202

Max Act: 1.3294. Min Act: -0.0000

Data Index: 311486 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 1.5202. Min Range: -1.5202

Max Act: 1.2368. Min Act: -0.0000

Data Index: 1130440 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 1.5202. Min Range: -1.5202

Max Act: 1.2374. Min Act: -0.0000

Data Index: 232679 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 1.5202. Min Range: -1.5202

Max Act: 1.1563. Min Act: -0.0000

Data Index: 978675 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 1.5202. Min Range: -1.5202

Max Act: 1.2226. Min Act: -0.0000

Data Index: 1009203 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 1.5202. Min Range: -1.5202

Max Act: 1.2219. Min Act: -0.0000

Data Index: 720149 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 1.5202. Min Range: -1.5202

Max Act: 1.2170. Min Act: -0.0000

Data Index: 1019121 (C4 (Web Text))

Max Activating Token Index: 7