Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 698 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.2388. Min Act: -0.0001

Data Index: 1462103 (Python Code)

Max Activating Token Index: 53

Text #1

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.2391. Min Act: -0.0001

Data Index: 838476 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.2191. Min Act: -0.0001

Data Index: 166649 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.2262. Min Act: -0.0001

Data Index: 293038 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.2139. Min Act: -0.0001

Data Index: 478826 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.2061. Min Act: -0.0001

Data Index: 1637498 (Python Code)

Max Activating Token Index: 91

Text #6

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.1906. Min Act: -0.0001

Data Index: 169560 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.2124. Min Act: -0.0001

Data Index: 1148606 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.1918. Min Act: -0.0001

Data Index: 1238650 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.2044. Min Act: -0.0001

Data Index: 66570 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.2110. Min Act: -0.0001

Data Index: 1511986 (Python Code)

Max Activating Token Index: 221

Text #11

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.1841. Min Act: -0.0001

Data Index: 936138 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.2012. Min Act: -0.0001

Data Index: 714328 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.2084. Min Act: -0.0001

Data Index: 730612 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.1940. Min Act: -0.0001

Data Index: 1151912 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.1867. Min Act: -0.0001

Data Index: 1210573 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.1985. Min Act: -0.0001

Data Index: 1191395 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.1905. Min Act: -0.0001

Data Index: 158082 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.1754. Min Act: -0.0001

Data Index: 702970 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 0.2391. Min Range: -0.2391

Max Act: 0.1939. Min Act: -0.0001

Data Index: 1389694 (Python Code)

Max Activating Token Index: 101