Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 759 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.5513. Min Act: -0.0000

Data Index: 1141922 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.5102. Min Act: -0.0000

Data Index: 1276403 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.4695. Min Act: -0.0000

Data Index: 245927 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.4764. Min Act: -0.0000

Data Index: 1306734 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.4326. Min Act: -0.0000

Data Index: 1418 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.4222. Min Act: -0.0000

Data Index: 140876 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.4041. Min Act: -0.0000

Data Index: 1339597 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.4310. Min Act: -0.0000

Data Index: 128888 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.4295. Min Act: -0.0000

Data Index: 466278 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.4232. Min Act: -0.0000

Data Index: 367930 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.3991. Min Act: -0.0000

Data Index: 675039 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.3964. Min Act: -0.0000

Data Index: 1037979 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.4115. Min Act: -0.0000

Data Index: 838411 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.4082. Min Act: -0.0000

Data Index: 1070421 (C4 (Web Text))

Max Activating Token Index: 750

Text #14

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.3950. Min Act: -0.0000

Data Index: 1203263 (C4 (Web Text))

Max Activating Token Index: 947

Text #15

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.3923. Min Act: -0.0000

Data Index: 122720 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.4044. Min Act: -0.0000

Data Index: 474596 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.4062. Min Act: -0.0000

Data Index: 91332 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.4432. Min Act: -0.0000

Data Index: 467567 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.4038. Min Act: -0.0000

Data Index: 722339 (C4 (Web Text))

Max Activating Token Index: 497