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

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

Neuron 3873 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5140. Min Range: -1.5140

Max Act: 1.5140. Min Act: -0.0000

Data Index: 740089 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 1.5140. Min Range: -1.5140

Max Act: 1.1543. Min Act: -0.0000

Data Index: 232848 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 1.5140. Min Range: -1.5140

Max Act: 1.1385. Min Act: -0.0000

Data Index: 340509 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 1.5140. Min Range: -1.5140

Max Act: 1.0866. Min Act: -0.0000

Data Index: 1095535 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 1.5140. Min Range: -1.5140

Max Act: 1.0787. Min Act: -0.0000

Data Index: 1356535 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 1.5140. Min Range: -1.5140

Max Act: 1.0683. Min Act: -0.0000

Data Index: 810103 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 1.5140. Min Range: -1.5140

Max Act: 1.1311. Min Act: -0.0000

Data Index: 7211 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 1.5140. Min Range: -1.5140

Max Act: 1.1166. Min Act: -0.0000

Data Index: 934497 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 1.5140. Min Range: -1.5140

Max Act: 1.0474. Min Act: -0.0000

Data Index: 896742 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 1.5140. Min Range: -1.5140

Max Act: 1.0423. Min Act: -0.0000

Data Index: 898434 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 1.5140. Min Range: -1.5140

Max Act: 1.0733. Min Act: -0.0000

Data Index: 772516 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 1.5140. Min Range: -1.5140

Max Act: 1.0723. Min Act: -0.0000

Data Index: 1093741 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 1.5140. Min Range: -1.5140

Max Act: 1.0245. Min Act: -0.0000

Data Index: 1041415 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 1.5140. Min Range: -1.5140

Max Act: 1.0481. Min Act: -0.0000

Data Index: 954149 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 1.5140. Min Range: -1.5140

Max Act: 1.1149. Min Act: -0.0000

Data Index: 494745 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 1.5140. Min Range: -1.5140

Max Act: 1.0501. Min Act: -0.0000

Data Index: 688725 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 1.5140. Min Range: -1.5140

Max Act: 1.0680. Min Act: -0.0000

Data Index: 1104734 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 1.5140. Min Range: -1.5140

Max Act: 1.0253. Min Act: -0.0000

Data Index: 1214480 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 1.5140. Min Range: -1.5140

Max Act: 1.0450. Min Act: -0.0000

Data Index: 1176677 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 1.5140. Min Range: -1.5140

Max Act: 1.0271. Min Act: -0.0000

Data Index: 492026 (C4 (Web Text))

Max Activating Token Index: 203