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

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

Neuron 1554 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.6246. Min Act: -0.0002

Data Index: 279454 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.6158. Min Act: -0.0001

Data Index: 880516 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.6072. Min Act: -0.0001

Data Index: 1146981 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.5839. Min Act: -0.0002

Data Index: 1262779 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.5987. Min Act: -0.0002

Data Index: 121983 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.5903. Min Act: -0.0002

Data Index: 1271778 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.6114. Min Act: -0.0001

Data Index: 494702 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.6058. Min Act: -0.0001

Data Index: 273408 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.5883. Min Act: -0.0002

Data Index: 1095108 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.5470. Min Act: -0.0002

Data Index: 841766 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.5782. Min Act: -0.0002

Data Index: 1338414 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.5605. Min Act: -0.0002

Data Index: 75235 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.5776. Min Act: -0.0002

Data Index: 1012336 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.5538. Min Act: -0.0002

Data Index: 187050 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.5705. Min Act: -0.0001

Data Index: 884800 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.5362. Min Act: -0.0001

Data Index: 639141 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.5511. Min Act: -0.0002

Data Index: 88748 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.5512. Min Act: -0.0002

Data Index: 817470 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.5699. Min Act: -0.0002

Data Index: 990040 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.5504. Min Act: -0.0001

Data Index: 1350577 (C4 (Web Text))

Max Activating Token Index: 31