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

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

Neuron 2211 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1082. Min Range: -1.1082

Max Act: 1.1082. Min Act: -0.0000

Data Index: 1425170 (Python Code)

Max Activating Token Index: 995

Text #1

Max Range: 1.1082. Min Range: -1.1082

Max Act: 1.0066. Min Act: -0.0000

Data Index: 1607639 (Python Code)

Max Activating Token Index: 982

Text #2

Max Range: 1.1082. Min Range: -1.1082

Max Act: 0.8823. Min Act: -0.0000

Data Index: 1100155 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 1.1082. Min Range: -1.1082

Max Act: 0.8854. Min Act: -0.0000

Data Index: 1084767 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 1.1082. Min Range: -1.1082

Max Act: 0.8437. Min Act: -0.0000

Data Index: 1088130 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 1.1082. Min Range: -1.1082

Max Act: 0.8996. Min Act: -0.0000

Data Index: 1151632 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 1.1082. Min Range: -1.1082

Max Act: 0.8979. Min Act: -0.0000

Data Index: 1211189 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 1.1082. Min Range: -1.1082

Max Act: 0.8742. Min Act: -0.0000

Data Index: 124333 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 1.1082. Min Range: -1.1082

Max Act: 0.8647. Min Act: -0.0000

Data Index: 564055 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 1.1082. Min Range: -1.1082

Max Act: 0.8632. Min Act: -0.0000

Data Index: 1053595 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 1.1082. Min Range: -1.1082

Max Act: 0.8443. Min Act: -0.0000

Data Index: 571498 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 1.1082. Min Range: -1.1082

Max Act: 0.8393. Min Act: -0.0000

Data Index: 275134 (C4 (Web Text))

Max Activating Token Index: 657

Text #12

Max Range: 1.1082. Min Range: -1.1082

Max Act: 0.8365. Min Act: -0.0000

Data Index: 889395 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 1.1082. Min Range: -1.1082

Max Act: 0.8355. Min Act: -0.0000

Data Index: 18997 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 1.1082. Min Range: -1.1082

Max Act: 0.7800. Min Act: -0.0000

Data Index: 136117 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 1.1082. Min Range: -1.1082

Max Act: 0.8233. Min Act: -0.0000

Data Index: 1493928 (Python Code)

Max Activating Token Index: 728

Text #16

Max Range: 1.1082. Min Range: -1.1082

Max Act: 0.8389. Min Act: -0.0000

Data Index: 1085407 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 1.1082. Min Range: -1.1082

Max Act: 0.8687. Min Act: -0.0000

Data Index: 1180538 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 1.1082. Min Range: -1.1082

Max Act: 0.8364. Min Act: -0.0000

Data Index: 1266605 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 1.1082. Min Range: -1.1082

Max Act: 0.7323. Min Act: -0.0000

Data Index: 435570 (C4 (Web Text))

Max Activating Token Index: 227