Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 913 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3986. Min Range: -1.3986

Max Act: 1.3986. Min Act: -0.0001

Data Index: 205681 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 1.3986. Min Range: -1.3986

Max Act: 1.3105. Min Act: -0.0001

Data Index: 359867 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 1.3986. Min Range: -1.3986

Max Act: 1.2318. Min Act: -0.0001

Data Index: 898710 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 1.3986. Min Range: -1.3986

Max Act: 1.2007. Min Act: -0.0001

Data Index: 771492 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 1.3986. Min Range: -1.3986

Max Act: 1.1871. Min Act: -0.0001

Data Index: 473280 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 1.3986. Min Range: -1.3986

Max Act: 1.0960. Min Act: -0.0001

Data Index: 1354889 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 1.3986. Min Range: -1.3986

Max Act: 1.0993. Min Act: -0.0001

Data Index: 1152894 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 1.3986. Min Range: -1.3986

Max Act: 1.0560. Min Act: -0.0001

Data Index: 1062678 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 1.3986. Min Range: -1.3986

Max Act: 1.1204. Min Act: -0.0001

Data Index: 355157 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 1.3986. Min Range: -1.3986

Max Act: 1.0066. Min Act: -0.0001

Data Index: 1294856 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 1.3986. Min Range: -1.3986

Max Act: 1.0207. Min Act: -0.0001

Data Index: 74796 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 1.3986. Min Range: -1.3986

Max Act: 1.0209. Min Act: -0.0001

Data Index: 133380 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 1.3986. Min Range: -1.3986

Max Act: 0.9994. Min Act: -0.0001

Data Index: 899535 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 1.3986. Min Range: -1.3986

Max Act: 0.9038. Min Act: -0.0001

Data Index: 1189660 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 1.3986. Min Range: -1.3986

Max Act: 0.9588. Min Act: -0.0001

Data Index: 793112 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 1.3986. Min Range: -1.3986

Max Act: 0.9288. Min Act: -0.0001

Data Index: 857215 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 1.3986. Min Range: -1.3986

Max Act: 0.9233. Min Act: -0.0001

Data Index: 1159495 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 1.3986. Min Range: -1.3986

Max Act: 0.8927. Min Act: -0.0001

Data Index: 621573 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 1.3986. Min Range: -1.3986

Max Act: 0.9052. Min Act: -0.0001

Data Index: 1222814 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 1.3986. Min Range: -1.3986

Max Act: 0.9550. Min Act: -0.0001

Data Index: 718440 (C4 (Web Text))

Max Activating Token Index: 779