Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2434 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1686. Min Act: -0.0001

Data Index: 906144 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1406. Min Act: -0.0001

Data Index: 856223 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1243. Min Act: -0.0001

Data Index: 769478 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1264. Min Act: -0.0001

Data Index: 88589 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1267. Min Act: -0.0001

Data Index: 9368 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1327. Min Act: -0.0001

Data Index: 241811 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1242. Min Act: -0.0001

Data Index: 674817 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1264. Min Act: -0.0001

Data Index: 981719 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1188. Min Act: -0.0001

Data Index: 611342 (C4 (Web Text))

Max Activating Token Index: 742

Text #9

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1100. Min Act: -0.0001

Data Index: 992704 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1298. Min Act: -0.0001

Data Index: 12331 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1145. Min Act: -0.0001

Data Index: 1312646 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1145. Min Act: -0.0001

Data Index: 1261063 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1113. Min Act: -0.0001

Data Index: 53082 (C4 (Web Text))

Max Activating Token Index: 919

Text #14

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1057. Min Act: -0.0001

Data Index: 985592 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1008. Min Act: -0.0001

Data Index: 1312653 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.0996. Min Act: -0.0001

Data Index: 1020583 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.0909. Min Act: -0.0001

Data Index: 1296967 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1088. Min Act: -0.0001

Data Index: 451928 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1019. Min Act: -0.0001

Data Index: 874116 (C4 (Web Text))

Max Activating Token Index: 1023