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

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

Neuron 1534 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1143. Min Act: -0.0000

Data Index: 36938 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0998. Min Act: -0.0000

Data Index: 1200745 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1021. Min Act: -0.0000

Data Index: 221400 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0892. Min Act: -0.0000

Data Index: 604606 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0913. Min Act: -0.0000

Data Index: 155406 (C4 (Web Text))

Max Activating Token Index: 773

Text #5

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0879. Min Act: -0.0000

Data Index: 410201 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1001. Min Act: -0.0000

Data Index: 1340055 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0949. Min Act: -0.0000

Data Index: 352626 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0827. Min Act: -0.0000

Data Index: 836807 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0910. Min Act: -0.0000

Data Index: 692498 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0858. Min Act: -0.0000

Data Index: 1277176 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0839. Min Act: -0.0000

Data Index: 963688 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0821. Min Act: -0.0000

Data Index: 365540 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0761. Min Act: -0.0000

Data Index: 891131 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0797. Min Act: -0.0000

Data Index: 729586 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0734. Min Act: -0.0000

Data Index: 812413 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0771. Min Act: -0.0000

Data Index: 460402 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0718. Min Act: -0.0000

Data Index: 438803 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0769. Min Act: -0.0000

Data Index: 102845 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0730. Min Act: -0.0000

Data Index: 1019307 (C4 (Web Text))

Max Activating Token Index: 387