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

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

Neuron 77 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9540. Min Range: -3.9540

Max Act: 3.9540. Min Act: -0.0001

Data Index: 944613 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 3.9540. Min Range: -3.9540

Max Act: 3.0911. Min Act: -0.0001

Data Index: 1357122 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 3.9540. Min Range: -3.9540

Max Act: 2.6134. Min Act: -0.0001

Data Index: 230368 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 3.9540. Min Range: -3.9540

Max Act: 2.8188. Min Act: -0.0001

Data Index: 1074399 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 3.9540. Min Range: -3.9540

Max Act: 2.4218. Min Act: -0.0001

Data Index: 644517 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 3.9540. Min Range: -3.9540

Max Act: 2.5066. Min Act: -0.0001

Data Index: 76839 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 3.9540. Min Range: -3.9540

Max Act: 2.1364. Min Act: -0.0001

Data Index: 1112204 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 3.9540. Min Range: -3.9540

Max Act: 2.1119. Min Act: -0.0001

Data Index: 371408 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 3.9540. Min Range: -3.9540

Max Act: 1.9230. Min Act: -0.0001

Data Index: 875761 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 3.9540. Min Range: -3.9540

Max Act: 2.0971. Min Act: -0.0001

Data Index: 1049253 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 3.9540. Min Range: -3.9540

Max Act: 2.0456. Min Act: -0.0001

Data Index: 810309 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 3.9540. Min Range: -3.9540

Max Act: 1.9343. Min Act: -0.0001

Data Index: 908540 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 3.9540. Min Range: -3.9540

Max Act: 1.9936. Min Act: -0.0001

Data Index: 583938 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 3.9540. Min Range: -3.9540

Max Act: 1.9926. Min Act: -0.0001

Data Index: 360898 (C4 (Web Text))

Max Activating Token Index: 878

Text #14

Max Range: 3.9540. Min Range: -3.9540

Max Act: 1.8382. Min Act: -0.0001

Data Index: 985639 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 3.9540. Min Range: -3.9540

Max Act: 1.9416. Min Act: -0.0001

Data Index: 857708 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 3.9540. Min Range: -3.9540

Max Act: 1.8041. Min Act: -0.0001

Data Index: 1339275 (C4 (Web Text))

Max Activating Token Index: 641

Text #17

Max Range: 3.9540. Min Range: -3.9540

Max Act: 1.7988. Min Act: -0.0001

Data Index: 592312 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 3.9540. Min Range: -3.9540

Max Act: 1.9537. Min Act: -0.0001

Data Index: 127701 (C4 (Web Text))

Max Activating Token Index: 504

Text #19

Max Range: 3.9540. Min Range: -3.9540

Max Act: 1.6154. Min Act: -0.0001

Data Index: 697682 (C4 (Web Text))

Max Activating Token Index: 152