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

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

Neuron 5185 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2425. Min Range: -1.2425

Max Act: 1.2425. Min Act: -0.0000

Data Index: 38403 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 1.2425. Min Range: -1.2425

Max Act: 1.1054. Min Act: -0.0000

Data Index: 702316 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 1.2425. Min Range: -1.2425

Max Act: 1.0300. Min Act: -0.0000

Data Index: 987959 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.8950. Min Act: -0.0000

Data Index: 100450 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.9875. Min Act: -0.0000

Data Index: 1152329 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.9458. Min Act: -0.0000

Data Index: 1332279 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.9621. Min Act: -0.0000

Data Index: 996864 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.9153. Min Act: -0.0000

Data Index: 482312 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.8743. Min Act: -0.0000

Data Index: 1137827 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.8367. Min Act: -0.0000

Data Index: 976957 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.9508. Min Act: -0.0000

Data Index: 508323 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.8422. Min Act: -0.0000

Data Index: 331126 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.8518. Min Act: -0.0000

Data Index: 902790 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.8081. Min Act: -0.0000

Data Index: 1329819 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.8107. Min Act: -0.0000

Data Index: 246238 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.7995. Min Act: -0.0000

Data Index: 768153 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.7982. Min Act: -0.0000

Data Index: 504795 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.7705. Min Act: -0.0000

Data Index: 829107 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.7412. Min Act: -0.0000

Data Index: 931788 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 1.2425. Min Range: -1.2425

Max Act: 0.7769. Min Act: -0.0000

Data Index: 1122584 (C4 (Web Text))

Max Activating Token Index: 894