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

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

Neuron 2705 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1769. Min Act: -0.0001

Data Index: 349740 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1324. Min Act: -0.0001

Data Index: 663980 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1346. Min Act: -0.0002

Data Index: 1086580 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1362. Min Act: -0.0001

Data Index: 747108 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1280. Min Act: -0.0001

Data Index: 101603 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1163. Min Act: -0.0002

Data Index: 24678 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1317. Min Act: -0.0002

Data Index: 1321087 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1125. Min Act: -0.0001

Data Index: 527263 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1094. Min Act: -0.0001

Data Index: 392651 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1139. Min Act: -0.0002

Data Index: 243705 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1096. Min Act: -0.0001

Data Index: 2913 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1078. Min Act: -0.0001

Data Index: 641579 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1031. Min Act: -0.0002

Data Index: 591632 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1044. Min Act: -0.0001

Data Index: 1063917 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1025. Min Act: -0.0001

Data Index: 860708 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1072. Min Act: -0.0001

Data Index: 882581 (C4 (Web Text))

Max Activating Token Index: 363

Text #16

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.0935. Min Act: -0.0002

Data Index: 16235 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.0985. Min Act: -0.0001

Data Index: 271509 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.0947. Min Act: -0.0001

Data Index: 1324134 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.0976. Min Act: -0.0001

Data Index: 726763 (C4 (Web Text))

Max Activating Token Index: 659