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

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

Neuron 5752 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1443. Min Act: -0.0000

Data Index: 1128663 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1264. Min Act: -0.0000

Data Index: 901659 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1132. Min Act: -0.0000

Data Index: 381741 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1109. Min Act: -0.0001

Data Index: 634649 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1093. Min Act: -0.0000

Data Index: 127214 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1044. Min Act: -0.0001

Data Index: 953914 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.0995. Min Act: -0.0000

Data Index: 132078 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1080. Min Act: -0.0000

Data Index: 45424 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1032. Min Act: -0.0001

Data Index: 65570 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.0963. Min Act: -0.0000

Data Index: 1280216 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.0974. Min Act: -0.0000

Data Index: 870728 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1036. Min Act: -0.0000

Data Index: 634560 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1008. Min Act: -0.0000

Data Index: 414934 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.0899. Min Act: -0.0001

Data Index: 1066820 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.0903. Min Act: -0.0000

Data Index: 358808 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.0942. Min Act: -0.0000

Data Index: 931770 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.0897. Min Act: -0.0000

Data Index: 1156765 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.0924. Min Act: -0.0001

Data Index: 123547 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.0889. Min Act: -0.0000

Data Index: 105753 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.0921. Min Act: -0.0000

Data Index: 1034634 (C4 (Web Text))

Max Activating Token Index: 689