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

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

Neuron 5363 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: 4.1005. Min Range: -4.1005

Max Act: 4.1005. Min Act: -0.0000

Data Index: 1281918 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 4.1005. Min Range: -4.1005

Max Act: 4.0656. Min Act: -0.0000

Data Index: 899520 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 4.1005. Min Range: -4.1005

Max Act: 4.0728. Min Act: -0.0000

Data Index: 472354 (C4 (Web Text))

Max Activating Token Index: 169

Text #3

Max Range: 4.1005. Min Range: -4.1005

Max Act: 3.7583. Min Act: -0.0000

Data Index: 1194370 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 4.1005. Min Range: -4.1005

Max Act: 3.5108. Min Act: -0.0000

Data Index: 1018265 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 4.1005. Min Range: -4.1005

Max Act: 3.2801. Min Act: -0.0000

Data Index: 1263284 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 4.1005. Min Range: -4.1005

Max Act: 3.2038. Min Act: -0.0000

Data Index: 70373 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 4.1005. Min Range: -4.1005

Max Act: 3.1900. Min Act: -0.0000

Data Index: 1170158 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 4.1005. Min Range: -4.1005

Max Act: 3.0778. Min Act: -0.0000

Data Index: 999799 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 4.1005. Min Range: -4.1005

Max Act: 2.9199. Min Act: -0.0000

Data Index: 1179481 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 4.1005. Min Range: -4.1005

Max Act: 3.0202. Min Act: -0.0000

Data Index: 938423 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 4.1005. Min Range: -4.1005

Max Act: 2.9959. Min Act: -0.0000

Data Index: 1118743 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 4.1005. Min Range: -4.1005

Max Act: 3.0010. Min Act: -0.0000

Data Index: 1140773 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 4.1005. Min Range: -4.1005

Max Act: 2.8317. Min Act: -0.0000

Data Index: 385877 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 4.1005. Min Range: -4.1005

Max Act: 3.0846. Min Act: -0.0000

Data Index: 1075739 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 4.1005. Min Range: -4.1005

Max Act: 2.9729. Min Act: -0.0000

Data Index: 649925 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 4.1005. Min Range: -4.1005

Max Act: 2.9619. Min Act: -0.0000

Data Index: 26877 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 4.1005. Min Range: -4.1005

Max Act: 2.9679. Min Act: -0.0000

Data Index: 503815 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 4.1005. Min Range: -4.1005

Max Act: 3.0931. Min Act: -0.0000

Data Index: 803591 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 4.1005. Min Range: -4.1005

Max Act: 2.7992. Min Act: -0.0000

Data Index: 106074 (C4 (Web Text))

Max Activating Token Index: 281