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

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

Neuron 106 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: 5.5541. Min Range: -5.5541

Max Act: 5.5541. Min Act: -0.0000

Data Index: 589779 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 5.5541. Min Range: -5.5541

Max Act: 5.5495. Min Act: -0.0000

Data Index: 307621 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 5.5541. Min Range: -5.5541

Max Act: 4.8464. Min Act: -0.0000

Data Index: 272942 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 5.5541. Min Range: -5.5541

Max Act: 4.7646. Min Act: -0.0000

Data Index: 1067616 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 5.5541. Min Range: -5.5541

Max Act: 5.1451. Min Act: -0.0000

Data Index: 1395636 (Python Code)

Max Activating Token Index: 587

Text #5

Max Range: 5.5541. Min Range: -5.5541

Max Act: 4.4937. Min Act: -0.0000

Data Index: 1035505 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 5.5541. Min Range: -5.5541

Max Act: 4.3328. Min Act: -0.0000

Data Index: 775389 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 5.5541. Min Range: -5.5541

Max Act: 4.2818. Min Act: -0.0000

Data Index: 259289 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 5.5541. Min Range: -5.5541

Max Act: 4.5546. Min Act: -0.0000

Data Index: 467166 (C4 (Web Text))

Max Activating Token Index: 765

Text #9

Max Range: 5.5541. Min Range: -5.5541

Max Act: 4.3059. Min Act: -0.0000

Data Index: 953215 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 5.5541. Min Range: -5.5541

Max Act: 3.9048. Min Act: -0.0000

Data Index: 1198088 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 5.5541. Min Range: -5.5541

Max Act: 3.9986. Min Act: -0.0000

Data Index: 1307164 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 5.5541. Min Range: -5.5541

Max Act: 3.9790. Min Act: -0.0000

Data Index: 804489 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 5.5541. Min Range: -5.5541

Max Act: 3.8371. Min Act: -0.0000

Data Index: 1021274 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 5.5541. Min Range: -5.5541

Max Act: 4.6957. Min Act: -0.0000

Data Index: 497865 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 5.5541. Min Range: -5.5541

Max Act: 3.9419. Min Act: -0.0000

Data Index: 904719 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 5.5541. Min Range: -5.5541

Max Act: 3.7755. Min Act: -0.0000

Data Index: 1127041 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 5.5541. Min Range: -5.5541

Max Act: 3.9222. Min Act: -0.0000

Data Index: 145335 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 5.5541. Min Range: -5.5541

Max Act: 4.0565. Min Act: -0.0000

Data Index: 60764 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 5.5541. Min Range: -5.5541

Max Act: 3.6825. Min Act: -0.0000

Data Index: 1259352 (C4 (Web Text))

Max Activating Token Index: 442