Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 508 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0277. Min Act: -0.0000

Data Index: 1435069 (Python Code)

Max Activating Token Index: 751

Text #1

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0210. Min Act: -0.0000

Data Index: 1592058 (Python Code)

Max Activating Token Index: 31

Text #2

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0233. Min Act: -0.0000

Data Index: 1224123 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0199. Min Act: -0.0000

Data Index: 1072108 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0190. Min Act: -0.0000

Data Index: 584605 (C4 (Web Text))

Max Activating Token Index: 853

Text #5

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0198. Min Act: -0.0001

Data Index: 737422 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0202. Min Act: -0.0000

Data Index: 533115 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0198. Min Act: -0.0000

Data Index: 583801 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0196. Min Act: -0.0000

Data Index: 758510 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0199. Min Act: -0.0000

Data Index: 394328 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0198. Min Act: -0.0000

Data Index: 1288622 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0192. Min Act: -0.0000

Data Index: 592399 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0186. Min Act: -0.0000

Data Index: 1221961 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0182. Min Act: -0.0000

Data Index: 969504 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0188. Min Act: -0.0000

Data Index: 356514 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0184. Min Act: -0.0000

Data Index: 190948 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0179. Min Act: -0.0000

Data Index: 961787 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0181. Min Act: -0.0000

Data Index: 53848 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0182. Min Act: -0.0000

Data Index: 919483 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0180. Min Act: -0.0000

Data Index: 1360670 (Python Code)

Max Activating Token Index: 118