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

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

Neuron 1405 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9968. Min Range: -2.9968

Max Act: 2.9236. Min Act: -0.0000

Data Index: 226369 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 2.9968. Min Range: -2.9968

Max Act: 2.9968. Min Act: -0.0000

Data Index: 475629 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 2.9968. Min Range: -2.9968

Max Act: 2.8124. Min Act: -0.0000

Data Index: 482422 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 2.9968. Min Range: -2.9968

Max Act: 2.4325. Min Act: -0.0000

Data Index: 1342671 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 2.9968. Min Range: -2.9968

Max Act: 2.2646. Min Act: -0.0000

Data Index: 877143 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 2.9968. Min Range: -2.9968

Max Act: 2.2070. Min Act: -0.0000

Data Index: 1185779 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 2.9968. Min Range: -2.9968

Max Act: 2.3995. Min Act: -0.0000

Data Index: 106905 (C4 (Web Text))

Max Activating Token Index: 28

Text #7

Max Range: 2.9968. Min Range: -2.9968

Max Act: 2.1129. Min Act: -0.0000

Data Index: 523323 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 2.9968. Min Range: -2.9968

Max Act: 2.2085. Min Act: -0.0000

Data Index: 1191593 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 2.9968. Min Range: -2.9968

Max Act: 2.0900. Min Act: -0.0000

Data Index: 577053 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 2.9968. Min Range: -2.9968

Max Act: 1.8958. Min Act: -0.0000

Data Index: 1313618 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 2.9968. Min Range: -2.9968

Max Act: 2.0791. Min Act: -0.0000

Data Index: 1126057 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 2.9968. Min Range: -2.9968

Max Act: 2.0525. Min Act: -0.0000

Data Index: 80188 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 2.9968. Min Range: -2.9968

Max Act: 2.1415. Min Act: -0.0000

Data Index: 87236 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 2.9968. Min Range: -2.9968

Max Act: 1.9211. Min Act: -0.0000

Data Index: 234350 (C4 (Web Text))

Max Activating Token Index: 456

Text #15

Max Range: 2.9968. Min Range: -2.9968

Max Act: 1.8224. Min Act: -0.0000

Data Index: 379081 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 2.9968. Min Range: -2.9968

Max Act: 1.9090. Min Act: -0.0000

Data Index: 375801 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 2.9968. Min Range: -2.9968

Max Act: 1.8729. Min Act: -0.0000

Data Index: 89598 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 2.9968. Min Range: -2.9968

Max Act: 1.8557. Min Act: -0.0000

Data Index: 732467 (C4 (Web Text))

Max Activating Token Index: 813

Text #19

Max Range: 2.9968. Min Range: -2.9968

Max Act: 1.8446. Min Act: -0.0000

Data Index: 867629 (C4 (Web Text))

Max Activating Token Index: 787