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

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

Neuron 3357 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2181. Min Range: -2.2181

Max Act: 2.2181. Min Act: -0.0000

Data Index: 86866 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 2.2181. Min Range: -2.2181

Max Act: 2.1492. Min Act: -0.0000

Data Index: 756986 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.7730. Min Act: -0.0001

Data Index: 130214 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.8166. Min Act: -0.0000

Data Index: 103052 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.7206. Min Act: -0.0000

Data Index: 839265 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.5192. Min Act: -0.0000

Data Index: 621934 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.7221. Min Act: -0.0001

Data Index: 231281 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.6367. Min Act: -0.0001

Data Index: 1277788 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.4968. Min Act: -0.0001

Data Index: 475809 (C4 (Web Text))

Max Activating Token Index: 718

Text #9

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.6226. Min Act: -0.0000

Data Index: 908635 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.7604. Min Act: -0.0001

Data Index: 781330 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.7490. Min Act: -0.0000

Data Index: 1298012 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.5595. Min Act: -0.0000

Data Index: 337544 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.5025. Min Act: -0.0001

Data Index: 522228 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.6143. Min Act: -0.0000

Data Index: 107526 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.5621. Min Act: -0.0000

Data Index: 1307503 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.4983. Min Act: -0.0000

Data Index: 1041037 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.4343. Min Act: -0.0001

Data Index: 185368 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.4528. Min Act: -0.0000

Data Index: 884653 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.3220. Min Act: -0.0000

Data Index: 1340861 (C4 (Web Text))

Max Activating Token Index: 134