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

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

Neuron 1975 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.4270. Min Act: -0.0000

Data Index: 26700 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.4415. Min Act: -0.0001

Data Index: 82388 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.4029. Min Act: -0.0001

Data Index: 317690 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3917. Min Act: -0.0000

Data Index: 265367 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3770. Min Act: -0.0000

Data Index: 1070458 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3699. Min Act: -0.0000

Data Index: 211973 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3668. Min Act: -0.0001

Data Index: 894990 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3513. Min Act: -0.0000

Data Index: 666162 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3471. Min Act: -0.0000

Data Index: 549343 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3479. Min Act: -0.0000

Data Index: 68759 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3456. Min Act: -0.0000

Data Index: 742070 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3269. Min Act: -0.0000

Data Index: 832403 (C4 (Web Text))

Max Activating Token Index: 862

Text #12

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3053. Min Act: 0.0001

Data Index: 1271583 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3188. Min Act: 0.0000

Data Index: 313314 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3010. Min Act: -0.0001

Data Index: 693821 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3090. Min Act: -0.0000

Data Index: 1235559 (C4 (Web Text))

Max Activating Token Index: 738

Text #16

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3082. Min Act: -0.0000

Data Index: 206926 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3063. Min Act: -0.0000

Data Index: 308508 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3157. Min Act: -0.0000

Data Index: 385764 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.2968. Min Act: -0.0000

Data Index: 1331778 (C4 (Web Text))

Max Activating Token Index: 94