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

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

Neuron 2230 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2270. Min Range: -3.2270

Max Act: 3.2270. Min Act: -0.0000

Data Index: 760601 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 3.2270. Min Range: -3.2270

Max Act: 2.4105. Min Act: -0.0001

Data Index: 578456 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 3.2270. Min Range: -3.2270

Max Act: 2.5207. Min Act: -0.0001

Data Index: 159663 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 3.2270. Min Range: -3.2270

Max Act: 2.0301. Min Act: -0.0000

Data Index: 1009517 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 3.2270. Min Range: -3.2270

Max Act: 2.1258. Min Act: -0.0001

Data Index: 918497 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 3.2270. Min Range: -3.2270

Max Act: 2.1066. Min Act: -0.0001

Data Index: 262045 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 3.2270. Min Range: -3.2270

Max Act: 2.0648. Min Act: -0.0001

Data Index: 21266 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 3.2270. Min Range: -3.2270

Max Act: 1.9361. Min Act: -0.0000

Data Index: 170115 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 3.2270. Min Range: -3.2270

Max Act: 1.8792. Min Act: -0.0000

Data Index: 581264 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 3.2270. Min Range: -3.2270

Max Act: 1.9248. Min Act: -0.0000

Data Index: 624971 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 3.2270. Min Range: -3.2270

Max Act: 1.8597. Min Act: -0.0001

Data Index: 412490 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 3.2270. Min Range: -3.2270

Max Act: 1.8987. Min Act: -0.0000

Data Index: 518376 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 3.2270. Min Range: -3.2270

Max Act: 1.8949. Min Act: -0.0001

Data Index: 41870 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 3.2270. Min Range: -3.2270

Max Act: 1.9242. Min Act: -0.0000

Data Index: 801201 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 3.2270. Min Range: -3.2270

Max Act: 1.8202. Min Act: -0.0000

Data Index: 657544 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 3.2270. Min Range: -3.2270

Max Act: 1.8258. Min Act: -0.0001

Data Index: 86322 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 3.2270. Min Range: -3.2270

Max Act: 1.7844. Min Act: -0.0000

Data Index: 1344949 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 3.2270. Min Range: -3.2270

Max Act: 1.7724. Min Act: -0.0001

Data Index: 1176202 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 3.2270. Min Range: -3.2270

Max Act: 1.5467. Min Act: -0.0000

Data Index: 1089180 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 3.2270. Min Range: -3.2270

Max Act: 1.7230. Min Act: -0.0000

Data Index: 1075292 (C4 (Web Text))

Max Activating Token Index: 856