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

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

Neuron 2465 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.2120. Min Act: -0.0001

Data Index: 1323838 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1897. Min Act: -0.0001

Data Index: 236035 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1579. Min Act: -0.0002

Data Index: 638726 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1617. Min Act: -0.0001

Data Index: 523913 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1546. Min Act: -0.0001

Data Index: 147321 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1558. Min Act: -0.0001

Data Index: 965242 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1419. Min Act: -0.0001

Data Index: 755044 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1413. Min Act: -0.0001

Data Index: 857776 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1202. Min Act: -0.0001

Data Index: 801081 (C4 (Web Text))

Max Activating Token Index: 170

Text #9

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1212. Min Act: -0.0001

Data Index: 1071532 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1102. Min Act: -0.0002

Data Index: 1334529 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1172. Min Act: -0.0001

Data Index: 1450781 (Python Code)

Max Activating Token Index: 403

Text #12

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1100. Min Act: -0.0002

Data Index: 662764 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.0994. Min Act: -0.0001

Data Index: 800186 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1025. Min Act: -0.0001

Data Index: 289997 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.0989. Min Act: -0.0001

Data Index: 53886 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.0872. Min Act: -0.0001

Data Index: 33395 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1012. Min Act: -0.0002

Data Index: 405257 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.0940. Min Act: -0.0001

Data Index: 722606 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.0988. Min Act: -0.0001

Data Index: 1277251 (C4 (Web Text))

Max Activating Token Index: 314