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

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

Neuron 2740 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.3899. Min Act: -0.0000

Data Index: 35247 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.3399. Min Act: -0.0000

Data Index: 687792 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.3742. Min Act: -0.0000

Data Index: 43880 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.2869. Min Act: -0.0001

Data Index: 1554144 (Python Code)

Max Activating Token Index: 669

Text #4

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.3129. Min Act: -0.0000

Data Index: 862312 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.3600. Min Act: -0.0001

Data Index: 1403890 (Python Code)

Max Activating Token Index: 526

Text #6

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.2921. Min Act: -0.0000

Data Index: 1028525 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.2877. Min Act: -0.0000

Data Index: 853680 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.3557. Min Act: -0.0000

Data Index: 1141392 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.2552. Min Act: -0.0000

Data Index: 1289739 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.3202. Min Act: -0.0000

Data Index: 1128566 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.3151. Min Act: -0.0001

Data Index: 1628176 (Python Code)

Max Activating Token Index: 209

Text #12

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.3156. Min Act: -0.0001

Data Index: 1639592 (Python Code)

Max Activating Token Index: 296

Text #13

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.2758. Min Act: -0.0000

Data Index: 1145496 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.3049. Min Act: -0.0000

Data Index: 637161 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.3086. Min Act: -0.0000

Data Index: 178335 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.3284. Min Act: -0.0000

Data Index: 692800 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.2888. Min Act: -0.0000

Data Index: 839987 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.2623. Min Act: -0.0000

Data Index: 1283340 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.2749. Min Act: -0.0000

Data Index: 983003 (C4 (Web Text))

Max Activating Token Index: 491