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

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

Neuron 5191 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0486. Min Act: -0.0001

Data Index: 1189613 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0479. Min Act: -0.0001

Data Index: 123843 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0452. Min Act: -0.0001

Data Index: 122471 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0448. Min Act: -0.0001

Data Index: 1089983 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0464. Min Act: -0.0001

Data Index: 148315 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0436. Min Act: -0.0001

Data Index: 1053031 (C4 (Web Text))

Max Activating Token Index: 568

Text #6

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0410. Min Act: -0.0001

Data Index: 728749 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0433. Min Act: -0.0001

Data Index: 1213561 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0397. Min Act: -0.0002

Data Index: 203462 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0409. Min Act: -0.0001

Data Index: 143119 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0432. Min Act: -0.0001

Data Index: 913567 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0435. Min Act: -0.0001

Data Index: 454749 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0412. Min Act: -0.0001

Data Index: 1247919 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0375. Min Act: -0.0001

Data Index: 1284750 (C4 (Web Text))

Max Activating Token Index: 991

Text #14

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0430. Min Act: -0.0001

Data Index: 566493 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0397. Min Act: -0.0001

Data Index: 450187 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0418. Min Act: -0.0001

Data Index: 1276289 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0396. Min Act: -0.0001

Data Index: 919423 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0421. Min Act: -0.0001

Data Index: 800113 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0381. Min Act: -0.0001

Data Index: 207307 (C4 (Web Text))

Max Activating Token Index: 889