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

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

Neuron 850 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2680. Min Range: -1.2680

Max Act: 1.1316. Min Act: -0.0002

Data Index: 883162 (C4 (Web Text))

Max Activating Token Index: 499

Text #1

Max Range: 1.2680. Min Range: -1.2680

Max Act: 1.0989. Min Act: -0.0002

Data Index: 1250610 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 1.2680. Min Range: -1.2680

Max Act: 1.1517. Min Act: -0.0001

Data Index: 563363 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 1.2680. Min Range: -1.2680

Max Act: 1.2680. Min Act: -0.0002

Data Index: 19083 (C4 (Web Text))

Max Activating Token Index: 623

Text #4

Max Range: 1.2680. Min Range: -1.2680

Max Act: 1.1511. Min Act: -0.0001

Data Index: 1309492 (C4 (Web Text))

Max Activating Token Index: 933

Text #5

Max Range: 1.2680. Min Range: -1.2680

Max Act: 0.9994. Min Act: -0.0001

Data Index: 238867 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 1.2680. Min Range: -1.2680

Max Act: 1.1089. Min Act: -0.0002

Data Index: 532989 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 1.2680. Min Range: -1.2680

Max Act: 1.0650. Min Act: -0.0001

Data Index: 537777 (C4 (Web Text))

Max Activating Token Index: 776

Text #8

Max Range: 1.2680. Min Range: -1.2680

Max Act: 1.0000. Min Act: -0.0002

Data Index: 859812 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 1.2680. Min Range: -1.2680

Max Act: 0.9646. Min Act: -0.0001

Data Index: 708102 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 1.2680. Min Range: -1.2680

Max Act: 1.0450. Min Act: -0.0001

Data Index: 929274 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 1.2680. Min Range: -1.2680

Max Act: 1.0350. Min Act: -0.0002

Data Index: 294452 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 1.2680. Min Range: -1.2680

Max Act: 0.9768. Min Act: -0.0002

Data Index: 1087984 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 1.2680. Min Range: -1.2680

Max Act: 1.0684. Min Act: -0.0002

Data Index: 315637 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 1.2680. Min Range: -1.2680

Max Act: 1.1263. Min Act: -0.0001

Data Index: 283147 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 1.2680. Min Range: -1.2680

Max Act: 1.1344. Min Act: -0.0001

Data Index: 212214 (C4 (Web Text))

Max Activating Token Index: 531

Text #16

Max Range: 1.2680. Min Range: -1.2680

Max Act: 0.8804. Min Act: -0.0002

Data Index: 1159157 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 1.2680. Min Range: -1.2680

Max Act: 0.9993. Min Act: -0.0002

Data Index: 413160 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 1.2680. Min Range: -1.2680

Max Act: 0.9377. Min Act: -0.0002

Data Index: 812289 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 1.2680. Min Range: -1.2680

Max Act: 1.0055. Min Act: -0.0002

Data Index: 982043 (C4 (Web Text))

Max Activating Token Index: 38