Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5050 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1271. Min Range: -2.1271

Max Act: 2.1271. Min Act: -0.0000

Data Index: 1208860 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 2.1271. Min Range: -2.1271

Max Act: 1.8354. Min Act: -0.0000

Data Index: 1017113 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 2.1271. Min Range: -2.1271

Max Act: 1.7459. Min Act: -0.0000

Data Index: 115948 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 2.1271. Min Range: -2.1271

Max Act: 1.7078. Min Act: -0.0000

Data Index: 244485 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 2.1271. Min Range: -2.1271

Max Act: 1.6705. Min Act: -0.0000

Data Index: 635729 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 2.1271. Min Range: -2.1271

Max Act: 1.6296. Min Act: -0.0000

Data Index: 975679 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 2.1271. Min Range: -2.1271

Max Act: 1.7194. Min Act: -0.0000

Data Index: 584789 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 2.1271. Min Range: -2.1271

Max Act: 1.4551. Min Act: -0.0000

Data Index: 1144919 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 2.1271. Min Range: -2.1271

Max Act: 1.5345. Min Act: -0.0000

Data Index: 283696 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 2.1271. Min Range: -2.1271

Max Act: 1.5302. Min Act: -0.0000

Data Index: 993769 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 2.1271. Min Range: -2.1271

Max Act: 1.6172. Min Act: -0.0000

Data Index: 1068305 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 2.1271. Min Range: -2.1271

Max Act: 1.4313. Min Act: -0.0000

Data Index: 717848 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 2.1271. Min Range: -2.1271

Max Act: 1.4996. Min Act: -0.0000

Data Index: 624261 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 2.1271. Min Range: -2.1271

Max Act: 1.4081. Min Act: -0.0000

Data Index: 786179 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 2.1271. Min Range: -2.1271

Max Act: 1.4644. Min Act: 0.0000

Data Index: 492940 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 2.1271. Min Range: -2.1271

Max Act: 1.4580. Min Act: -0.0000

Data Index: 956789 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 2.1271. Min Range: -2.1271

Max Act: 1.3844. Min Act: -0.0000

Data Index: 1050285 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 2.1271. Min Range: -2.1271

Max Act: 1.3718. Min Act: -0.0000

Data Index: 441767 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 2.1271. Min Range: -2.1271

Max Act: 1.4405. Min Act: -0.0000

Data Index: 26104 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 2.1271. Min Range: -2.1271

Max Act: 1.3331. Min Act: -0.0000

Data Index: 711938 (C4 (Web Text))

Max Activating Token Index: 208