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

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

Neuron 1109 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1312. Min Act: -0.0001

Data Index: 1289496 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1359. Min Act: -0.0001

Data Index: 363121 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1255. Min Act: -0.0001

Data Index: 791286 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1206. Min Act: -0.0001

Data Index: 1067934 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1178. Min Act: -0.0001

Data Index: 18786 (C4 (Web Text))

Max Activating Token Index: 343

Text #5

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1141. Min Act: -0.0001

Data Index: 673644 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0956. Min Act: -0.0001

Data Index: 44753 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0995. Min Act: -0.0001

Data Index: 509865 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0992. Min Act: -0.0000

Data Index: 1147435 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0951. Min Act: -0.0000

Data Index: 1251999 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0923. Min Act: -0.0001

Data Index: 946324 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0912. Min Act: -0.0001

Data Index: 1278406 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0952. Min Act: -0.0001

Data Index: 1160418 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0944. Min Act: -0.0001

Data Index: 1078315 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0905. Min Act: -0.0001

Data Index: 734230 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0869. Min Act: -0.0001

Data Index: 52487 (C4 (Web Text))

Max Activating Token Index: 769

Text #16

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0878. Min Act: -0.0001

Data Index: 406283 (C4 (Web Text))

Max Activating Token Index: 326

Text #17

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0853. Min Act: -0.0001

Data Index: 515665 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0839. Min Act: -0.0000

Data Index: 581230 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0866. Min Act: -0.0001

Data Index: 679484 (C4 (Web Text))

Max Activating Token Index: 90