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

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

Neuron 5991 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: 1.7272. Min Range: -1.7272

Max Act: 1.7272. Min Act: -0.0002

Data Index: 1095907 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.6958. Min Act: -0.0002

Data Index: 131442 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.6464. Min Act: -0.0002

Data Index: 1292155 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.6337. Min Act: -0.0002

Data Index: 997287 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.5225. Min Act: -0.0003

Data Index: 391702 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.5223. Min Act: -0.0002

Data Index: 826311 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.4761. Min Act: -0.0002

Data Index: 396712 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.4929. Min Act: -0.0002

Data Index: 744879 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.4434. Min Act: -0.0002

Data Index: 381568 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.4869. Min Act: -0.0002

Data Index: 633524 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.4458. Min Act: -0.0002

Data Index: 1083019 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.4490. Min Act: -0.0002

Data Index: 97956 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.4286. Min Act: -0.0002

Data Index: 191743 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.4354. Min Act: -0.0003

Data Index: 1104215 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.4280. Min Act: -0.0002

Data Index: 759711 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.4142. Min Act: -0.0002

Data Index: 212873 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.4129. Min Act: -0.0002

Data Index: 446274 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.4357. Min Act: -0.0002

Data Index: 976970 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.4151. Min Act: -0.0002

Data Index: 790244 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 1.7272. Min Range: -1.7272

Max Act: 1.3979. Min Act: -0.0002

Data Index: 276610 (C4 (Web Text))

Max Activating Token Index: 636