Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1600 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3272. Min Range: -1.3272

Max Act: 1.3272. Min Act: -0.0001

Data Index: 655712 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 1.3272. Min Range: -1.3272

Max Act: 1.3012. Min Act: -0.0001

Data Index: 868800 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 1.3272. Min Range: -1.3272

Max Act: 1.2128. Min Act: -0.0001

Data Index: 1053420 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 1.3272. Min Range: -1.3272

Max Act: 1.2719. Min Act: -0.0001

Data Index: 509067 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 1.3272. Min Range: -1.3272

Max Act: 1.2639. Min Act: -0.0001

Data Index: 919325 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 1.3272. Min Range: -1.3272

Max Act: 1.2069. Min Act: -0.0001

Data Index: 1132061 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 1.3272. Min Range: -1.3272

Max Act: 1.1781. Min Act: -0.0001

Data Index: 1078131 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 1.3272. Min Range: -1.3272

Max Act: 1.1814. Min Act: -0.0001

Data Index: 1074426 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 1.3272. Min Range: -1.3272

Max Act: 1.1218. Min Act: -0.0001

Data Index: 153844 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 1.3272. Min Range: -1.3272

Max Act: 1.1468. Min Act: -0.0001

Data Index: 236019 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 1.3272. Min Range: -1.3272

Max Act: 1.1313. Min Act: -0.0001

Data Index: 1154009 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 1.3272. Min Range: -1.3272

Max Act: 1.1487. Min Act: -0.0001

Data Index: 730211 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 1.3272. Min Range: -1.3272

Max Act: 1.1981. Min Act: -0.0001

Data Index: 261384 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 1.3272. Min Range: -1.3272

Max Act: 1.1465. Min Act: -0.0001

Data Index: 1103397 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 1.3272. Min Range: -1.3272

Max Act: 1.1349. Min Act: -0.0001

Data Index: 67685 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 1.3272. Min Range: -1.3272

Max Act: 1.1274. Min Act: -0.0001

Data Index: 489140 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 1.3272. Min Range: -1.3272

Max Act: 1.1290. Min Act: -0.0001

Data Index: 1280783 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 1.3272. Min Range: -1.3272

Max Act: 1.1323. Min Act: -0.0001

Data Index: 1292154 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 1.3272. Min Range: -1.3272

Max Act: 1.0948. Min Act: -0.0001

Data Index: 816373 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 1.3272. Min Range: -1.3272

Max Act: 1.0837. Min Act: -0.0001

Data Index: 307939 (C4 (Web Text))

Max Activating Token Index: 911