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

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

Neuron 303 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3970. Min Range: -3.3970

Max Act: 3.3970. Min Act: -0.0001

Data Index: 612211 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 3.3970. Min Range: -3.3970

Max Act: 2.8699. Min Act: -0.0000

Data Index: 218371 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 3.3970. Min Range: -3.3970

Max Act: 3.0122. Min Act: -0.0000

Data Index: 221572 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 3.3970. Min Range: -3.3970

Max Act: 2.8965. Min Act: -0.0001

Data Index: 328023 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 3.3970. Min Range: -3.3970

Max Act: 3.0211. Min Act: -0.0001

Data Index: 933024 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 3.3970. Min Range: -3.3970

Max Act: 2.8128. Min Act: -0.0001

Data Index: 186088 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 3.3970. Min Range: -3.3970

Max Act: 2.7577. Min Act: -0.0001

Data Index: 905834 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 3.3970. Min Range: -3.3970

Max Act: 2.7490. Min Act: -0.0001

Data Index: 1248115 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 3.3970. Min Range: -3.3970

Max Act: 2.6822. Min Act: -0.0000

Data Index: 368816 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 3.3970. Min Range: -3.3970

Max Act: 2.8363. Min Act: -0.0001

Data Index: 1070669 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 3.3970. Min Range: -3.3970

Max Act: 2.7041. Min Act: -0.0001

Data Index: 587627 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 3.3970. Min Range: -3.3970

Max Act: 2.6933. Min Act: -0.0001

Data Index: 1255418 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 3.3970. Min Range: -3.3970

Max Act: 2.6658. Min Act: -0.0000

Data Index: 134094 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 3.3970. Min Range: -3.3970

Max Act: 2.7959. Min Act: -0.0001

Data Index: 1004632 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 3.3970. Min Range: -3.3970

Max Act: 2.4754. Min Act: -0.0000

Data Index: 236099 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 3.3970. Min Range: -3.3970

Max Act: 2.5849. Min Act: -0.0001

Data Index: 451606 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 3.3970. Min Range: -3.3970

Max Act: 2.4629. Min Act: -0.0001

Data Index: 1308049 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 3.3970. Min Range: -3.3970

Max Act: 2.5865. Min Act: -0.0001

Data Index: 168989 (C4 (Web Text))

Max Activating Token Index: 758

Text #18

Max Range: 3.3970. Min Range: -3.3970

Max Act: 2.6847. Min Act: -0.0001

Data Index: 180476 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 3.3970. Min Range: -3.3970

Max Act: 2.5738. Min Act: -0.0000

Data Index: 812937 (C4 (Web Text))

Max Activating Token Index: 92