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

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

Neuron 5695 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.3170. Min Range: -1.3170

Max Act: 1.3170. Min Act: -0.0002

Data Index: 315968 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 1.3170. Min Range: -1.3170

Max Act: 1.3038. Min Act: -0.0002

Data Index: 158920 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 1.3170. Min Range: -1.3170

Max Act: 1.2711. Min Act: -0.0002

Data Index: 1089885 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 1.3170. Min Range: -1.3170

Max Act: 1.2656. Min Act: -0.0002

Data Index: 93900 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 1.3170. Min Range: -1.3170

Max Act: 1.2505. Min Act: -0.0002

Data Index: 338898 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 1.3170. Min Range: -1.3170

Max Act: 1.2395. Min Act: -0.0002

Data Index: 860247 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 1.3170. Min Range: -1.3170

Max Act: 1.2238. Min Act: -0.0002

Data Index: 1211899 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 1.3170. Min Range: -1.3170

Max Act: 1.2283. Min Act: -0.0002

Data Index: 790593 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 1.3170. Min Range: -1.3170

Max Act: 1.1513. Min Act: -0.0002

Data Index: 872751 (C4 (Web Text))

Max Activating Token Index: 1010

Text #9

Max Range: 1.3170. Min Range: -1.3170

Max Act: 1.1662. Min Act: -0.0002

Data Index: 400740 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 1.3170. Min Range: -1.3170

Max Act: 1.1614. Min Act: -0.0002

Data Index: 261282 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 1.3170. Min Range: -1.3170

Max Act: 1.1283. Min Act: -0.0002

Data Index: 426706 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 1.3170. Min Range: -1.3170

Max Act: 1.1501. Min Act: -0.0002

Data Index: 227658 (C4 (Web Text))

Max Activating Token Index: 759

Text #13

Max Range: 1.3170. Min Range: -1.3170

Max Act: 1.1129. Min Act: -0.0002

Data Index: 1285272 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 1.3170. Min Range: -1.3170

Max Act: 1.1085. Min Act: -0.0002

Data Index: 1249799 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 1.3170. Min Range: -1.3170

Max Act: 1.1306. Min Act: -0.0002

Data Index: 1218763 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 1.3170. Min Range: -1.3170

Max Act: 1.1007. Min Act: -0.0002

Data Index: 850176 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 1.3170. Min Range: -1.3170

Max Act: 1.1074. Min Act: -0.0002

Data Index: 991246 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 1.3170. Min Range: -1.3170

Max Act: 1.0966. Min Act: -0.0002

Data Index: 100414 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 1.3170. Min Range: -1.3170

Max Act: 1.1044. Min Act: -0.0002

Data Index: 314605 (C4 (Web Text))

Max Activating Token Index: 233