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

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

Neuron 1711 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.4742. Min Act: -0.0000

Data Index: 1247579 (C4 (Web Text))

Max Activating Token Index: 316

Text #1

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.4473. Min Act: -0.0000

Data Index: 555519 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.4773. Min Act: -0.0000

Data Index: 1064806 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.4344. Min Act: -0.0000

Data Index: 595912 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.4519. Min Act: -0.0000

Data Index: 893384 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.4495. Min Act: -0.0000

Data Index: 1191854 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3866. Min Act: -0.0000

Data Index: 1362533 (Python Code)

Max Activating Token Index: 988

Text #7

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.4588. Min Act: -0.0000

Data Index: 899608 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.4114. Min Act: -0.0000

Data Index: 714913 (C4 (Web Text))

Max Activating Token Index: 564

Text #9

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.4300. Min Act: -0.0000

Data Index: 19949 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.4212. Min Act: -0.0000

Data Index: 1157211 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3713. Min Act: -0.0000

Data Index: 876691 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3893. Min Act: -0.0000

Data Index: 815311 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.4065. Min Act: -0.0000

Data Index: 560084 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.4248. Min Act: -0.0000

Data Index: 1257406 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3841. Min Act: -0.0000

Data Index: 972948 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.4075. Min Act: -0.0000

Data Index: 277402 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3661. Min Act: -0.0000

Data Index: 509226 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.4121. Min Act: -0.0000

Data Index: 1538332 (Python Code)

Max Activating Token Index: 1009

Text #19

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3916. Min Act: -0.0000

Data Index: 7746 (C4 (Web Text))

Max Activating Token Index: 565