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

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

Neuron 5846 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0703. Min Range: -1.0703

Max Act: 1.0703. Min Act: -0.0000

Data Index: 874840 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.8686. Min Act: -0.0000

Data Index: 820377 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.8260. Min Act: 0.0001

Data Index: 54159 (C4 (Web Text))

Max Activating Token Index: 881

Text #3

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.7711. Min Act: -0.0000

Data Index: 1060730 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.8128. Min Act: -0.0000

Data Index: 408822 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.7883. Min Act: 0.0000

Data Index: 958583 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.7699. Min Act: 0.0000

Data Index: 876394 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.7106. Min Act: -0.0000

Data Index: 1188191 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.7478. Min Act: -0.0000

Data Index: 790774 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.7463. Min Act: -0.0000

Data Index: 970816 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.7347. Min Act: -0.0000

Data Index: 659068 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.7092. Min Act: -0.0000

Data Index: 732882 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.6996. Min Act: 0.0000

Data Index: 729633 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.7286. Min Act: -0.0000

Data Index: 669923 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.6299. Min Act: 0.0001

Data Index: 204492 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.6694. Min Act: 0.0000

Data Index: 1260686 (C4 (Web Text))

Max Activating Token Index: 975

Text #16

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.6673. Min Act: -0.0000

Data Index: 670173 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.7115. Min Act: -0.0000

Data Index: 37503 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.6652. Min Act: -0.0000

Data Index: 857532 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 1.0703. Min Range: -1.0703

Max Act: 0.7110. Min Act: 0.0000

Data Index: 963641 (C4 (Web Text))

Max Activating Token Index: 276