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

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

Neuron 2612 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0676. Min Act: -0.0002

Data Index: 936796 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0542. Min Act: -0.0002

Data Index: 848179 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0622. Min Act: -0.0002

Data Index: 412299 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0622. Min Act: -0.0002

Data Index: 509586 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0523. Min Act: -0.0002

Data Index: 926379 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0595. Min Act: -0.0002

Data Index: 1178051 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0555. Min Act: -0.0002

Data Index: 127757 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0552. Min Act: -0.0002

Data Index: 637738 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0512. Min Act: -0.0002

Data Index: 542823 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0564. Min Act: -0.0002

Data Index: 75994 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0524. Min Act: -0.0002

Data Index: 279593 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0597. Min Act: -0.0002

Data Index: 864246 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0531. Min Act: -0.0002

Data Index: 542058 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0541. Min Act: -0.0002

Data Index: 67936 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1164229 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0560. Min Act: -0.0002

Data Index: 1007296 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0475. Min Act: -0.0002

Data Index: 966654 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0548. Min Act: -0.0002

Data Index: 975151 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0546. Min Act: -0.0002

Data Index: 294297 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0491. Min Act: -0.0002

Data Index: 1220891 (C4 (Web Text))

Max Activating Token Index: 774