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

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

Neuron 1648 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3148. Min Range: -0.3148

Max Act: 0.3148. Min Act: -0.0000

Data Index: 827054 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 0.3148. Min Range: -0.3148

Max Act: 0.3101. Min Act: -0.0000

Data Index: 770537 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 0.3148. Min Range: -0.3148

Max Act: 0.2993. Min Act: -0.0000

Data Index: 1021023 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 0.3148. Min Range: -0.3148

Max Act: 0.2957. Min Act: -0.0000

Data Index: 924364 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.3148. Min Range: -0.3148

Max Act: 0.2940. Min Act: -0.0000

Data Index: 27535 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 0.3148. Min Range: -0.3148

Max Act: 0.2815. Min Act: -0.0000

Data Index: 304152 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 0.3148. Min Range: -0.3148

Max Act: 0.2842. Min Act: -0.0000

Data Index: 859922 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 0.3148. Min Range: -0.3148

Max Act: 0.2825. Min Act: -0.0000

Data Index: 958043 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 0.3148. Min Range: -0.3148

Max Act: 0.2896. Min Act: -0.0000

Data Index: 748103 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 0.3148. Min Range: -0.3148

Max Act: 0.2885. Min Act: -0.0000

Data Index: 223628 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 0.3148. Min Range: -0.3148

Max Act: 0.2828. Min Act: -0.0001

Data Index: 1207456 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 0.3148. Min Range: -0.3148

Max Act: 0.2734. Min Act: -0.0000

Data Index: 856002 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 0.3148. Min Range: -0.3148

Max Act: 0.2814. Min Act: -0.0000

Data Index: 946357 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.3148. Min Range: -0.3148

Max Act: 0.2658. Min Act: -0.0000

Data Index: 362657 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 0.3148. Min Range: -0.3148

Max Act: 0.2652. Min Act: -0.0000

Data Index: 1268352 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 0.3148. Min Range: -0.3148

Max Act: 0.2539. Min Act: -0.0000

Data Index: 43064 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 0.3148. Min Range: -0.3148

Max Act: 0.2505. Min Act: -0.0000

Data Index: 602256 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 0.3148. Min Range: -0.3148

Max Act: 0.2569. Min Act: -0.0000

Data Index: 9692 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 0.3148. Min Range: -0.3148

Max Act: 0.2395. Min Act: -0.0000

Data Index: 777249 (C4 (Web Text))

Max Activating Token Index: 868

Text #19

Max Range: 0.3148. Min Range: -0.3148

Max Act: 0.2549. Min Act: -0.0000

Data Index: 214827 (C4 (Web Text))

Max Activating Token Index: 383