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

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

Neuron 773 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4675. Min Act: -0.0000

Data Index: 362797 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4648. Min Act: -0.0000

Data Index: 1488595 (Python Code)

Max Activating Token Index: 71

Text #2

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4647. Min Act: -0.0000

Data Index: 938525 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4722. Min Act: -0.0000

Data Index: 1531816 (Python Code)

Max Activating Token Index: 306

Text #4

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4451. Min Act: -0.0000

Data Index: 212998 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4209. Min Act: -0.0000

Data Index: 575825 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4347. Min Act: -0.0000

Data Index: 1210489 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4301. Min Act: -0.0000

Data Index: 414937 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4391. Min Act: -0.0000

Data Index: 1612148 (Python Code)

Max Activating Token Index: 749

Text #9

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3999. Min Act: -0.0000

Data Index: 689651 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4118. Min Act: -0.0000

Data Index: 561266 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4032. Min Act: -0.0000

Data Index: 540878 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4037. Min Act: -0.0000

Data Index: 36630 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4132. Min Act: -0.0000

Data Index: 1323879 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3875. Min Act: -0.0000

Data Index: 168825 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3997. Min Act: -0.0000

Data Index: 1194712 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3984. Min Act: -0.0000

Data Index: 1282954 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3992. Min Act: -0.0000

Data Index: 591154 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3976. Min Act: -0.0000

Data Index: 1309953 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4132. Min Act: -0.0000

Data Index: 1042190 (C4 (Web Text))

Max Activating Token Index: 770