Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 262 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.6932. Min Act: -0.0001

Data Index: 744289 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.5995. Min Act: -0.0001

Data Index: 585919 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.6285. Min Act: -0.0001

Data Index: 93426 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.5880. Min Act: -0.0001

Data Index: 1083753 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.6024. Min Act: -0.0001

Data Index: 235780 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.6379. Min Act: -0.0001

Data Index: 671475 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.6004. Min Act: -0.0001

Data Index: 420289 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.6076. Min Act: -0.0001

Data Index: 1162021 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.6632. Min Act: -0.0001

Data Index: 613872 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.5809. Min Act: -0.0001

Data Index: 1244852 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.5972. Min Act: -0.0001

Data Index: 1127245 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.6544. Min Act: -0.0001

Data Index: 390151 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.6145. Min Act: -0.0001

Data Index: 604316 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.5324. Min Act: -0.0001

Data Index: 1025248 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.5827. Min Act: -0.0001

Data Index: 1116556 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.5858. Min Act: -0.0001

Data Index: 749783 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.6062. Min Act: -0.0001

Data Index: 1240597 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.5680. Min Act: -0.0001

Data Index: 703792 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.5917. Min Act: -0.0001

Data Index: 162693 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.5866. Min Act: -0.0001

Data Index: 629276 (C4 (Web Text))

Max Activating Token Index: 818