Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1915 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0400. Min Act: -0.0006

Data Index: 964221 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0388. Min Act: -0.0006

Data Index: 683181 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0318. Min Act: -0.0006

Data Index: 1026720 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0304. Min Act: -0.0006

Data Index: 686951 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0287. Min Act: -0.0006

Data Index: 1251394 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0277. Min Act: -0.0006

Data Index: 529098 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0283. Min Act: -0.0006

Data Index: 426677 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0287. Min Act: -0.0006

Data Index: 275140 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0263. Min Act: -0.0006

Data Index: 1051844 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0267. Min Act: -0.0006

Data Index: 1323122 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0274. Min Act: -0.0006

Data Index: 796061 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0268. Min Act: -0.0006

Data Index: 608799 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0267. Min Act: -0.0006

Data Index: 82885 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0265. Min Act: -0.0006

Data Index: 827988 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0263. Min Act: -0.0006

Data Index: 1137186 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0261. Min Act: -0.0006

Data Index: 294291 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0262. Min Act: -0.0006

Data Index: 1117928 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0261. Min Act: -0.0006

Data Index: 679502 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0261. Min Act: -0.0006

Data Index: 88010 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0255. Min Act: -0.0006

Data Index: 474409 (C4 (Web Text))

Max Activating Token Index: 859