Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2470 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.9232. Min Range: -2.9232

Max Act: 2.9232. Min Act: -0.0000

Data Index: 915526 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 2.9232. Min Range: -2.9232

Max Act: 2.7764. Min Act: -0.0000

Data Index: 879963 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 2.9232. Min Range: -2.9232

Max Act: 2.4902. Min Act: -0.0000

Data Index: 1159232 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 2.9232. Min Range: -2.9232

Max Act: 2.7146. Min Act: -0.0000

Data Index: 120669 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 2.9232. Min Range: -2.9232

Max Act: 2.5190. Min Act: -0.0000

Data Index: 102948 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 2.9232. Min Range: -2.9232

Max Act: 2.2391. Min Act: -0.0000

Data Index: 726402 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 2.9232. Min Range: -2.9232

Max Act: 2.4080. Min Act: -0.0000

Data Index: 1308627 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 2.9232. Min Range: -2.9232

Max Act: 2.4175. Min Act: -0.0000

Data Index: 1280468 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 2.9232. Min Range: -2.9232

Max Act: 2.4552. Min Act: -0.0000

Data Index: 454610 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 2.9232. Min Range: -2.9232

Max Act: 2.3038. Min Act: -0.0000

Data Index: 933909 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 2.9232. Min Range: -2.9232

Max Act: 2.2418. Min Act: -0.0000

Data Index: 351539 (C4 (Web Text))

Max Activating Token Index: 571

Text #11

Max Range: 2.9232. Min Range: -2.9232

Max Act: 2.2609. Min Act: -0.0000

Data Index: 882864 (C4 (Web Text))

Max Activating Token Index: 997

Text #12

Max Range: 2.9232. Min Range: -2.9232

Max Act: 1.9872. Min Act: -0.0000

Data Index: 621727 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 2.9232. Min Range: -2.9232

Max Act: 2.0576. Min Act: -0.0000

Data Index: 620468 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 2.9232. Min Range: -2.9232

Max Act: 2.0124. Min Act: -0.0000

Data Index: 1130259 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 2.9232. Min Range: -2.9232

Max Act: 2.0644. Min Act: -0.0000

Data Index: 137675 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 2.9232. Min Range: -2.9232

Max Act: 2.1064. Min Act: -0.0000

Data Index: 1084303 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 2.9232. Min Range: -2.9232

Max Act: 1.9327. Min Act: -0.0000

Data Index: 660661 (C4 (Web Text))

Max Activating Token Index: 173

Text #18

Max Range: 2.9232. Min Range: -2.9232

Max Act: 1.9927. Min Act: -0.0000

Data Index: 593911 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 2.9232. Min Range: -2.9232

Max Act: 2.1415. Min Act: -0.0000

Data Index: 1200722 (C4 (Web Text))

Max Activating Token Index: 390