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

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

Neuron 5422 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.6651. Min Range: -3.6651

Max Act: 3.6651. Min Act: -0.0000

Data Index: 312774 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 3.6651. Min Range: -3.6651

Max Act: 3.6336. Min Act: -0.0000

Data Index: 109846 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 3.6651. Min Range: -3.6651

Max Act: 2.9129. Min Act: -0.0000

Data Index: 524688 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 3.6651. Min Range: -3.6651

Max Act: 3.4181. Min Act: -0.0000

Data Index: 274812 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 3.6651. Min Range: -3.6651

Max Act: 3.5060. Min Act: -0.0000

Data Index: 83700 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 3.6651. Min Range: -3.6651

Max Act: 3.1735. Min Act: -0.0000

Data Index: 85231 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 3.6651. Min Range: -3.6651

Max Act: 3.0837. Min Act: -0.0000

Data Index: 309143 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 3.6651. Min Range: -3.6651

Max Act: 2.9951. Min Act: -0.0000

Data Index: 768402 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 3.6651. Min Range: -3.6651

Max Act: 2.8102. Min Act: -0.0000

Data Index: 1270043 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 3.6651. Min Range: -3.6651

Max Act: 2.8969. Min Act: -0.0000

Data Index: 810079 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 3.6651. Min Range: -3.6651

Max Act: 3.0497. Min Act: -0.0000

Data Index: 655435 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 3.6651. Min Range: -3.6651

Max Act: 3.0195. Min Act: -0.0000

Data Index: 172358 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 3.6651. Min Range: -3.6651

Max Act: 3.0235. Min Act: -0.0000

Data Index: 43602 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 3.6651. Min Range: -3.6651

Max Act: 3.0140. Min Act: -0.0000

Data Index: 715467 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 3.6651. Min Range: -3.6651

Max Act: 2.8342. Min Act: -0.0000

Data Index: 825021 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 3.6651. Min Range: -3.6651

Max Act: 3.0775. Min Act: -0.0000

Data Index: 408077 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 3.6651. Min Range: -3.6651

Max Act: 2.9368. Min Act: -0.0000

Data Index: 688942 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 3.6651. Min Range: -3.6651

Max Act: 2.8662. Min Act: -0.0000

Data Index: 102486 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 3.6651. Min Range: -3.6651

Max Act: 2.7010. Min Act: -0.0000

Data Index: 545956 (C4 (Web Text))

Max Activating Token Index: 830

Text #19

Max Range: 3.6651. Min Range: -3.6651

Max Act: 2.6978. Min Act: -0.0000

Data Index: 170886 (C4 (Web Text))

Max Activating Token Index: 957