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

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

Neuron 2823 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1601. Min Act: -0.0001

Data Index: 707091 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1632. Min Act: -0.0001

Data Index: 717699 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1376. Min Act: -0.0001

Data Index: 1070685 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1271. Min Act: -0.0001

Data Index: 1316425 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1197. Min Act: -0.0001

Data Index: 1149270 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1199. Min Act: -0.0001

Data Index: 923603 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1179. Min Act: -0.0001

Data Index: 241270 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1118. Min Act: -0.0001

Data Index: 770338 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1075. Min Act: -0.0001

Data Index: 325589 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1046. Min Act: -0.0001

Data Index: 438394 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.0966. Min Act: -0.0001

Data Index: 431766 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.0974. Min Act: -0.0001

Data Index: 919549 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.0821. Min Act: -0.0001

Data Index: 66593 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1009. Min Act: -0.0001

Data Index: 479975 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.0959. Min Act: -0.0000

Data Index: 1058936 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.0967. Min Act: -0.0000

Data Index: 1140401 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.0950. Min Act: -0.0001

Data Index: 494733 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1010. Min Act: -0.0000

Data Index: 1305463 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.0920. Min Act: -0.0001

Data Index: 360434 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.0908. Min Act: -0.0001

Data Index: 275558 (C4 (Web Text))

Max Activating Token Index: 544