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

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

Neuron 522 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: 0.5700. Min Range: -0.5700

Max Act: 0.5671. Min Act: -0.0000

Data Index: 813743 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.5700. Min Act: -0.0000

Data Index: 400819 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.5070. Min Act: -0.0000

Data Index: 486726 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.5105. Min Act: -0.0000

Data Index: 631368 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.5053. Min Act: -0.0000

Data Index: 274698 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.4980. Min Act: -0.0000

Data Index: 577011 (C4 (Web Text))

Max Activating Token Index: 196

Text #6

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.4912. Min Act: -0.0001

Data Index: 768473 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.4924. Min Act: -0.0000

Data Index: 1084707 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.4913. Min Act: -0.0000

Data Index: 294152 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.4740. Min Act: -0.0000

Data Index: 69171 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.4474. Min Act: -0.0000

Data Index: 350502 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.4377. Min Act: -0.0000

Data Index: 16703 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.4552. Min Act: -0.0001

Data Index: 912388 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.4448. Min Act: -0.0000

Data Index: 672006 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.4161. Min Act: -0.0000

Data Index: 1196792 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.4411. Min Act: -0.0001

Data Index: 522326 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.4072. Min Act: -0.0000

Data Index: 1265799 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.4238. Min Act: -0.0000

Data Index: 1064772 (C4 (Web Text))

Max Activating Token Index: 962

Text #18

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.4214. Min Act: -0.0001

Data Index: 52959 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.4309. Min Act: -0.0001

Data Index: 1084863 (C4 (Web Text))

Max Activating Token Index: 430