Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2696 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.1200. Min Act: -0.0000

Data Index: 856701 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.1168. Min Act: -0.0000

Data Index: 1344738 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.1073. Min Act: -0.0000

Data Index: 720488 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.1008. Min Act: -0.0000

Data Index: 103254 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.1038. Min Act: -0.0000

Data Index: 693579 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.1000. Min Act: -0.0000

Data Index: 596671 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.1002. Min Act: -0.0000

Data Index: 1347460 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0994. Min Act: -0.0000

Data Index: 1091574 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.1029. Min Act: -0.0000

Data Index: 40946 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0955. Min Act: -0.0001

Data Index: 501478 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0990. Min Act: -0.0000

Data Index: 753691 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0952. Min Act: -0.0001

Data Index: 920071 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0988. Min Act: -0.0000

Data Index: 745337 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0954. Min Act: -0.0000

Data Index: 781495 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0953. Min Act: -0.0000

Data Index: 1249697 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0934. Min Act: -0.0000

Data Index: 791576 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0947. Min Act: -0.0000

Data Index: 1242998 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0898. Min Act: -0.0000

Data Index: 964010 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0883. Min Act: -0.0000

Data Index: 729151 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0879. Min Act: -0.0000

Data Index: 592318 (C4 (Web Text))

Max Activating Token Index: 91