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

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

Neuron 2049 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: 0.3099. Min Range: -0.3099

Max Act: 0.2907. Min Act: -0.0001

Data Index: 689126 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.3099. Min Act: -0.0001

Data Index: 116284 (C4 (Web Text))

Max Activating Token Index: 737

Text #2

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2925. Min Act: -0.0001

Data Index: 709649 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2679. Min Act: -0.0001

Data Index: 154630 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2532. Min Act: -0.0001

Data Index: 1043970 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2470. Min Act: -0.0001

Data Index: 1070381 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2644. Min Act: -0.0001

Data Index: 613280 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2548. Min Act: -0.0001

Data Index: 1010721 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2481. Min Act: -0.0001

Data Index: 740611 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2391. Min Act: -0.0001

Data Index: 579268 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2384. Min Act: -0.0001

Data Index: 579760 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2467. Min Act: -0.0001

Data Index: 278840 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2315. Min Act: -0.0001

Data Index: 932697 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2352. Min Act: -0.0001

Data Index: 878371 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2256. Min Act: -0.0001

Data Index: 448778 (C4 (Web Text))

Max Activating Token Index: 1017

Text #15

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2214. Min Act: -0.0001

Data Index: 249245 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2327. Min Act: -0.0002

Data Index: 780708 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2270. Min Act: -0.0002

Data Index: 1018622 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2215. Min Act: -0.0001

Data Index: 1198249 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2363. Min Act: -0.0001

Data Index: 1355984 (C4 (Web Text))

Max Activating Token Index: 483