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

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

Neuron 5756 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.1478. Min Range: -8.1478

Max Act: 8.1444. Min Act: -0.0000

Data Index: 964548 (C4 (Web Text))

Max Activating Token Index: 859

Text #1

Max Range: 8.1478. Min Range: -8.1478

Max Act: 8.1478. Min Act: -0.0000

Data Index: 118453 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 8.1478. Min Range: -8.1478

Max Act: 7.8522. Min Act: -0.0000

Data Index: 750161 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 8.1478. Min Range: -8.1478

Max Act: 7.0502. Min Act: -0.0000

Data Index: 304065 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 8.1478. Min Range: -8.1478

Max Act: 7.0518. Min Act: -0.0000

Data Index: 374676 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 8.1478. Min Range: -8.1478

Max Act: 6.5287. Min Act: -0.0000

Data Index: 1291303 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 8.1478. Min Range: -8.1478

Max Act: 6.4837. Min Act: -0.0000

Data Index: 19936 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 8.1478. Min Range: -8.1478

Max Act: 6.4905. Min Act: -0.0000

Data Index: 338004 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 8.1478. Min Range: -8.1478

Max Act: 6.7118. Min Act: -0.0000

Data Index: 106182 (C4 (Web Text))

Max Activating Token Index: 660

Text #9

Max Range: 8.1478. Min Range: -8.1478

Max Act: 6.6661. Min Act: -0.0000

Data Index: 788098 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 8.1478. Min Range: -8.1478

Max Act: 6.6164. Min Act: -0.0000

Data Index: 385317 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 8.1478. Min Range: -8.1478

Max Act: 6.3743. Min Act: -0.0000

Data Index: 556366 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 8.1478. Min Range: -8.1478

Max Act: 6.0362. Min Act: -0.0000

Data Index: 581373 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 8.1478. Min Range: -8.1478

Max Act: 5.9417. Min Act: -0.0000

Data Index: 298540 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 8.1478. Min Range: -8.1478

Max Act: 5.4711. Min Act: -0.0000

Data Index: 559808 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 8.1478. Min Range: -8.1478

Max Act: 5.6003. Min Act: -0.0000

Data Index: 644865 (C4 (Web Text))

Max Activating Token Index: 939

Text #16

Max Range: 8.1478. Min Range: -8.1478

Max Act: 5.3812. Min Act: -0.0000

Data Index: 669558 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 8.1478. Min Range: -8.1478

Max Act: 5.3159. Min Act: -0.0000

Data Index: 364721 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 8.1478. Min Range: -8.1478

Max Act: 5.3338. Min Act: -0.0000

Data Index: 1057825 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 8.1478. Min Range: -8.1478

Max Act: 5.3318. Min Act: -0.0000

Data Index: 493282 (C4 (Web Text))

Max Activating Token Index: 804