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

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

Neuron 5215 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3260. Min Range: -2.3260

Max Act: 2.0705. Min Act: -0.0000

Data Index: 351173 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 2.3260. Min Range: -2.3260

Max Act: 2.3260. Min Act: -0.0000

Data Index: 935397 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 2.3260. Min Range: -2.3260

Max Act: 1.9402. Min Act: -0.0000

Data Index: 9569 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 2.3260. Min Range: -2.3260

Max Act: 1.7069. Min Act: -0.0000

Data Index: 1248294 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 2.3260. Min Range: -2.3260

Max Act: 1.5827. Min Act: -0.0000

Data Index: 1488324 (Python Code)

Max Activating Token Index: 714

Text #5

Max Range: 2.3260. Min Range: -2.3260

Max Act: 1.3676. Min Act: -0.0000

Data Index: 376181 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 2.3260. Min Range: -2.3260

Max Act: 1.2186. Min Act: 0.0000

Data Index: 589273 (C4 (Web Text))

Max Activating Token Index: 526

Text #7

Max Range: 2.3260. Min Range: -2.3260

Max Act: 1.2080. Min Act: -0.0000

Data Index: 1641433 (Python Code)

Max Activating Token Index: 644

Text #8

Max Range: 2.3260. Min Range: -2.3260

Max Act: 1.2058. Min Act: -0.0000

Data Index: 154229 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 2.3260. Min Range: -2.3260

Max Act: 1.1335. Min Act: 0.0000

Data Index: 1071070 (C4 (Web Text))

Max Activating Token Index: 296

Text #10

Max Range: 2.3260. Min Range: -2.3260

Max Act: 1.1294. Min Act: -0.0000

Data Index: 807588 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 2.3260. Min Range: -2.3260

Max Act: 1.1076. Min Act: -0.0000

Data Index: 437006 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 2.3260. Min Range: -2.3260

Max Act: 1.1059. Min Act: -0.0000

Data Index: 87342 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 2.3260. Min Range: -2.3260

Max Act: 1.0865. Min Act: -0.0000

Data Index: 927710 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 2.3260. Min Range: -2.3260

Max Act: 1.0742. Min Act: -0.0000

Data Index: 607298 (C4 (Web Text))

Max Activating Token Index: 134

Text #15

Max Range: 2.3260. Min Range: -2.3260

Max Act: 1.0061. Min Act: -0.0000

Data Index: 422806 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 2.3260. Min Range: -2.3260

Max Act: 1.0688. Min Act: -0.0000

Data Index: 1330135 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 2.3260. Min Range: -2.3260

Max Act: 1.0073. Min Act: -0.0000

Data Index: 1642937 (Python Code)

Max Activating Token Index: 868

Text #18

Max Range: 2.3260. Min Range: -2.3260

Max Act: 1.0571. Min Act: -0.0000

Data Index: 1030902 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 2.3260. Min Range: -2.3260

Max Act: 1.0494. Min Act: -0.0000

Data Index: 591765 (C4 (Web Text))

Max Activating Token Index: 130