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

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

Neuron 2344 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: 1.3194. Min Range: -1.3194

Max Act: 1.3194. Min Act: -0.0001

Data Index: 1250123 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 1.3194. Min Range: -1.3194

Max Act: 1.1563. Min Act: -0.0000

Data Index: 769939 (C4 (Web Text))

Max Activating Token Index: 1010

Text #2

Max Range: 1.3194. Min Range: -1.3194

Max Act: 1.0697. Min Act: -0.0001

Data Index: 106145 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 1.3194. Min Range: -1.3194

Max Act: 1.1172. Min Act: -0.0000

Data Index: 518763 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 1.3194. Min Range: -1.3194

Max Act: 1.0831. Min Act: -0.0000

Data Index: 805887 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 1.3194. Min Range: -1.3194

Max Act: 1.0779. Min Act: -0.0000

Data Index: 654794 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 1.3194. Min Range: -1.3194

Max Act: 1.0120. Min Act: -0.0001

Data Index: 638941 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 1.3194. Min Range: -1.3194

Max Act: 0.9865. Min Act: -0.0001

Data Index: 98038 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 1.3194. Min Range: -1.3194

Max Act: 1.0485. Min Act: -0.0001

Data Index: 26337 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 1.3194. Min Range: -1.3194

Max Act: 1.0120. Min Act: -0.0001

Data Index: 946406 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 1.3194. Min Range: -1.3194

Max Act: 0.9903. Min Act: -0.0001

Data Index: 897903 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 1.3194. Min Range: -1.3194

Max Act: 0.9048. Min Act: -0.0001

Data Index: 1076280 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 1.3194. Min Range: -1.3194

Max Act: 0.9364. Min Act: -0.0001

Data Index: 465741 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 1.3194. Min Range: -1.3194

Max Act: 0.9463. Min Act: -0.0001

Data Index: 304980 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 1.3194. Min Range: -1.3194

Max Act: 0.9039. Min Act: -0.0001

Data Index: 208962 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 1.3194. Min Range: -1.3194

Max Act: 0.9109. Min Act: -0.0001

Data Index: 1281606 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 1.3194. Min Range: -1.3194

Max Act: 0.9197. Min Act: -0.0001

Data Index: 522103 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 1.3194. Min Range: -1.3194

Max Act: 0.8904. Min Act: -0.0000

Data Index: 1257745 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 1.3194. Min Range: -1.3194

Max Act: 0.8630. Min Act: -0.0001

Data Index: 417407 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 1.3194. Min Range: -1.3194

Max Act: 0.8917. Min Act: -0.0000

Data Index: 200951 (C4 (Web Text))

Max Activating Token Index: 967