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

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

Neuron 6070 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4272. Min Range: -1.4272

Max Act: 1.4272. Min Act: -0.0001

Data Index: 1194642 (C4 (Web Text))

Max Activating Token Index: 926

Text #1

Max Range: 1.4272. Min Range: -1.4272

Max Act: 1.0611. Min Act: -0.0001

Data Index: 102036 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 1.4272. Min Range: -1.4272

Max Act: 0.9868. Min Act: -0.0001

Data Index: 504920 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 1.4272. Min Range: -1.4272

Max Act: 1.0515. Min Act: -0.0001

Data Index: 603603 (C4 (Web Text))

Max Activating Token Index: 731

Text #4

Max Range: 1.4272. Min Range: -1.4272

Max Act: 1.1027. Min Act: -0.0001

Data Index: 1075986 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 1.4272. Min Range: -1.4272

Max Act: 0.9721. Min Act: -0.0001

Data Index: 839154 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 1.4272. Min Range: -1.4272

Max Act: 0.9259. Min Act: -0.0001

Data Index: 435632 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 1.4272. Min Range: -1.4272

Max Act: 0.9644. Min Act: -0.0001

Data Index: 45980 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 1.4272. Min Range: -1.4272

Max Act: 0.9607. Min Act: -0.0001

Data Index: 430025 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 1.4272. Min Range: -1.4272

Max Act: 1.0217. Min Act: -0.0001

Data Index: 1185353 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 1.4272. Min Range: -1.4272

Max Act: 1.0040. Min Act: -0.0001

Data Index: 502302 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 1.4272. Min Range: -1.4272

Max Act: 0.8807. Min Act: -0.0001

Data Index: 349389 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 1.4272. Min Range: -1.4272

Max Act: 0.9898. Min Act: -0.0001

Data Index: 504117 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 1.4272. Min Range: -1.4272

Max Act: 0.9687. Min Act: -0.0001

Data Index: 445486 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 1.4272. Min Range: -1.4272

Max Act: 0.8838. Min Act: -0.0001

Data Index: 839036 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 1.4272. Min Range: -1.4272

Max Act: 0.9508. Min Act: -0.0001

Data Index: 806737 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 1.4272. Min Range: -1.4272

Max Act: 0.8965. Min Act: -0.0001

Data Index: 276370 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 1.4272. Min Range: -1.4272

Max Act: 0.9550. Min Act: -0.0001

Data Index: 113550 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 1.4272. Min Range: -1.4272

Max Act: 0.9143. Min Act: -0.0001

Data Index: 74374 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 1.4272. Min Range: -1.4272

Max Act: 0.9617. Min Act: -0.0001

Data Index: 1076744 (C4 (Web Text))

Max Activating Token Index: 743