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

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

Neuron 5963 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.4324. Min Act: -0.0001

Data Index: 329246 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.2093. Min Act: -0.0001

Data Index: 190247 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.2009. Min Act: -0.0001

Data Index: 1127399 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 1.4324. Min Range: -1.4324

Max Act: 0.8395. Min Act: -0.0001

Data Index: 964526 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.1199. Min Act: -0.0001

Data Index: 655418 (C4 (Web Text))

Max Activating Token Index: 609

Text #5

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.0875. Min Act: -0.0001

Data Index: 379887 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 1.4324. Min Range: -1.4324

Max Act: 0.9462. Min Act: -0.0001

Data Index: 721991 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 1.4324. Min Range: -1.4324

Max Act: 0.9036. Min Act: -0.0001

Data Index: 1368406 (Python Code)

Max Activating Token Index: 170

Text #8

Max Range: 1.4324. Min Range: -1.4324

Max Act: 0.6551. Min Act: -0.0001

Data Index: 528817 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 1.4324. Min Range: -1.4324

Max Act: 1.0342. Min Act: -0.0001

Data Index: 147615 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 1.4324. Min Range: -1.4324

Max Act: 0.9391. Min Act: -0.0001

Data Index: 1356829 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 1.4324. Min Range: -1.4324

Max Act: 0.8777. Min Act: -0.0001

Data Index: 1235414 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 1.4324. Min Range: -1.4324

Max Act: 0.9017. Min Act: -0.0001

Data Index: 242727 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 1.4324. Min Range: -1.4324

Max Act: 0.9057. Min Act: -0.0001

Data Index: 735374 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 1.4324. Min Range: -1.4324

Max Act: 0.9086. Min Act: -0.0001

Data Index: 178228 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 1.4324. Min Range: -1.4324

Max Act: 0.8695. Min Act: -0.0001

Data Index: 1143639 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 1.4324. Min Range: -1.4324

Max Act: 0.9178. Min Act: -0.0001

Data Index: 566766 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 1.4324. Min Range: -1.4324

Max Act: 0.8746. Min Act: -0.0001

Data Index: 578806 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 1.4324. Min Range: -1.4324

Max Act: 0.8737. Min Act: -0.0001

Data Index: 210799 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 1.4324. Min Range: -1.4324

Max Act: 0.8801. Min Act: -0.0001

Data Index: 1095172 (C4 (Web Text))

Max Activating Token Index: 932