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

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

Neuron 2453 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.8680. Min Act: -0.0000

Data Index: 947235 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.7825. Min Act: -0.0000

Data Index: 1146248 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.7643. Min Act: -0.0000

Data Index: 108349 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.7906. Min Act: -0.0000

Data Index: 570744 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.6818. Min Act: -0.0000

Data Index: 507667 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.6704. Min Act: -0.0000

Data Index: 1254929 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.6340. Min Act: -0.0000

Data Index: 1217148 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.6554. Min Act: -0.0000

Data Index: 1014667 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.6318. Min Act: -0.0000

Data Index: 1284100 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.6258. Min Act: -0.0000

Data Index: 815714 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.6215. Min Act: -0.0000

Data Index: 1353819 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.6114. Min Act: -0.0000

Data Index: 135147 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.5963. Min Act: -0.0000

Data Index: 624432 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.6082. Min Act: -0.0000

Data Index: 111375 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.5825. Min Act: -0.0000

Data Index: 489134 (C4 (Web Text))

Max Activating Token Index: 403

Text #15

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.5806. Min Act: -0.0000

Data Index: 1086688 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.5923. Min Act: -0.0000

Data Index: 553159 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.5927. Min Act: -0.0000

Data Index: 945807 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.5901. Min Act: -0.0000

Data Index: 1297079 (C4 (Web Text))

Max Activating Token Index: 818

Text #19

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.5944. Min Act: -0.0000

Data Index: 373746 (C4 (Web Text))

Max Activating Token Index: 506