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

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

Neuron 1271 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0846. Min Range: -1.0846

Max Act: 1.0702. Min Act: 0.0000

Data Index: 877103 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.9843. Min Act: -0.0000

Data Index: 453787 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 1.0846. Min Range: -1.0846

Max Act: 1.0846. Min Act: -0.0000

Data Index: 317882 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.7574. Min Act: -0.0000

Data Index: 10560 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.7299. Min Act: -0.0001

Data Index: 1146923 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.7421. Min Act: -0.0000

Data Index: 1191770 (C4 (Web Text))

Max Activating Token Index: 428

Text #6

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.7029. Min Act: -0.0000

Data Index: 1292684 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.6961. Min Act: -0.0000

Data Index: 361367 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.7252. Min Act: -0.0000

Data Index: 666829 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.7176. Min Act: -0.0000

Data Index: 615940 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.6847. Min Act: -0.0000

Data Index: 1216616 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.7062. Min Act: -0.0001

Data Index: 409389 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.6960. Min Act: -0.0000

Data Index: 345309 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.6694. Min Act: -0.0001

Data Index: 1002231 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.6845. Min Act: -0.0000

Data Index: 595662 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.6471. Min Act: -0.0000

Data Index: 730882 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.6597. Min Act: -0.0001

Data Index: 1157945 (C4 (Web Text))

Max Activating Token Index: 992

Text #17

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.7000. Min Act: -0.0000

Data Index: 1187084 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.6320. Min Act: -0.0000

Data Index: 105743 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.6674. Min Act: -0.0001

Data Index: 299845 (C4 (Web Text))

Max Activating Token Index: 790