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

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

Neuron 4045 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6118. Min Range: -0.6118

Max Act: 0.6118. Min Act: -0.0000

Data Index: 951707 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 0.6118. Min Range: -0.6118

Max Act: 0.5438. Min Act: -0.0000

Data Index: 709534 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 0.6118. Min Range: -0.6118

Max Act: 0.5020. Min Act: -0.0000

Data Index: 1277213 (C4 (Web Text))

Max Activating Token Index: 169

Text #3

Max Range: 0.6118. Min Range: -0.6118

Max Act: 0.5129. Min Act: -0.0000

Data Index: 656126 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 0.6118. Min Range: -0.6118

Max Act: 0.4948. Min Act: -0.0000

Data Index: 828125 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 0.6118. Min Range: -0.6118

Max Act: 0.4938. Min Act: -0.0001

Data Index: 702248 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 0.6118. Min Range: -0.6118

Max Act: 0.4895. Min Act: -0.0000

Data Index: 1311676 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 0.6118. Min Range: -0.6118

Max Act: 0.4982. Min Act: -0.0001

Data Index: 409327 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 0.6118. Min Range: -0.6118

Max Act: 0.4765. Min Act: -0.0000

Data Index: 743026 (C4 (Web Text))

Max Activating Token Index: 482

Text #9

Max Range: 0.6118. Min Range: -0.6118

Max Act: 0.4640. Min Act: -0.0001

Data Index: 604288 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 0.6118. Min Range: -0.6118

Max Act: 0.4956. Min Act: -0.0000

Data Index: 1096110 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 0.6118. Min Range: -0.6118

Max Act: 0.4616. Min Act: -0.0001

Data Index: 1274415 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 0.6118. Min Range: -0.6118

Max Act: 0.4368. Min Act: -0.0000

Data Index: 146650 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 0.6118. Min Range: -0.6118

Max Act: 0.4510. Min Act: -0.0000

Data Index: 448814 (C4 (Web Text))

Max Activating Token Index: 766

Text #14

Max Range: 0.6118. Min Range: -0.6118

Max Act: 0.4522. Min Act: -0.0001

Data Index: 505449 (C4 (Web Text))

Max Activating Token Index: 212

Text #15

Max Range: 0.6118. Min Range: -0.6118

Max Act: 0.4520. Min Act: -0.0000

Data Index: 1155456 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 0.6118. Min Range: -0.6118

Max Act: 0.4251. Min Act: -0.0000

Data Index: 681742 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 0.6118. Min Range: -0.6118

Max Act: 0.4295. Min Act: -0.0001

Data Index: 804805 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 0.6118. Min Range: -0.6118

Max Act: 0.4135. Min Act: -0.0000

Data Index: 924319 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 0.6118. Min Range: -0.6118

Max Act: 0.3986. Min Act: -0.0001

Data Index: 1315763 (C4 (Web Text))

Max Activating Token Index: 931