Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 530 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0265. Min Act: -0.0006

Data Index: 1214731 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0254. Min Act: -0.0006

Data Index: 467849 (C4 (Web Text))

Max Activating Token Index: 922

Text #2

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0246. Min Act: -0.0006

Data Index: 595058 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0239. Min Act: -0.0006

Data Index: 740787 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0244. Min Act: -0.0006

Data Index: 114720 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0242. Min Act: -0.0006

Data Index: 250406 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0239. Min Act: -0.0006

Data Index: 1237784 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0240. Min Act: -0.0006

Data Index: 396254 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0246. Min Act: -0.0006

Data Index: 1295058 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0245. Min Act: -0.0006

Data Index: 228808 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0244. Min Act: -0.0006

Data Index: 1239433 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0239. Min Act: -0.0006

Data Index: 1248468 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0244. Min Act: -0.0006

Data Index: 333844 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0236. Min Act: -0.0006

Data Index: 488068 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0238. Min Act: -0.0006

Data Index: 1018207 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0238. Min Act: -0.0006

Data Index: 951383 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0237. Min Act: -0.0006

Data Index: 1215393 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0236. Min Act: -0.0006

Data Index: 805179 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0239. Min Act: -0.0006

Data Index: 524428 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0233. Min Act: -0.0006

Data Index: 641694 (C4 (Web Text))

Max Activating Token Index: 328