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

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

Neuron 550 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5115. Min Range: -3.5115

Max Act: 3.5115. Min Act: -0.0000

Data Index: 1019183 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 3.5115. Min Range: -3.5115

Max Act: 3.3390. Min Act: -0.0001

Data Index: 421217 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 3.5115. Min Range: -3.5115

Max Act: 3.1741. Min Act: -0.0001

Data Index: 876446 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 3.5115. Min Range: -3.5115

Max Act: 3.1544. Min Act: -0.0001

Data Index: 1094428 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 3.5115. Min Range: -3.5115

Max Act: 3.3224. Min Act: -0.0000

Data Index: 475223 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 3.5115. Min Range: -3.5115

Max Act: 3.3013. Min Act: -0.0001

Data Index: 467963 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 3.5115. Min Range: -3.5115

Max Act: 3.2312. Min Act: -0.0001

Data Index: 279151 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 3.5115. Min Range: -3.5115

Max Act: 3.1650. Min Act: -0.0000

Data Index: 862871 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 3.5115. Min Range: -3.5115

Max Act: 3.0192. Min Act: -0.0000

Data Index: 971341 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 3.5115. Min Range: -3.5115

Max Act: 3.1268. Min Act: -0.0001

Data Index: 693168 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 3.5115. Min Range: -3.5115

Max Act: 2.8238. Min Act: -0.0001

Data Index: 653883 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 3.5115. Min Range: -3.5115

Max Act: 2.9171. Min Act: -0.0001

Data Index: 1083557 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 3.5115. Min Range: -3.5115

Max Act: 2.8271. Min Act: -0.0001

Data Index: 1308667 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 3.5115. Min Range: -3.5115

Max Act: 2.8653. Min Act: -0.0001

Data Index: 383040 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 3.5115. Min Range: -3.5115

Max Act: 2.9949. Min Act: -0.0001

Data Index: 744914 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 3.5115. Min Range: -3.5115

Max Act: 2.8147. Min Act: -0.0001

Data Index: 1344210 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 3.5115. Min Range: -3.5115

Max Act: 2.7901. Min Act: -0.0001

Data Index: 959922 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 3.5115. Min Range: -3.5115

Max Act: 2.6629. Min Act: -0.0000

Data Index: 782337 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 3.5115. Min Range: -3.5115

Max Act: 2.6607. Min Act: -0.0001

Data Index: 490355 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 3.5115. Min Range: -3.5115

Max Act: 2.5004. Min Act: -0.0001

Data Index: 1169739 (C4 (Web Text))

Max Activating Token Index: 51