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

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

Neuron 2557 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7000. Min Range: -1.7000

Max Act: 1.6288. Min Act: -0.0001

Data Index: 712193 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 1.7000. Min Range: -1.7000

Max Act: 1.7000. Min Act: -0.0001

Data Index: 115219 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 1.7000. Min Range: -1.7000

Max Act: 1.5386. Min Act: -0.0001

Data Index: 1173547 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 1.7000. Min Range: -1.7000

Max Act: 1.5297. Min Act: -0.0001

Data Index: 1095409 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 1.7000. Min Range: -1.7000

Max Act: 1.4353. Min Act: -0.0001

Data Index: 1093489 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 1.7000. Min Range: -1.7000

Max Act: 1.3552. Min Act: -0.0001

Data Index: 974428 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 1.7000. Min Range: -1.7000

Max Act: 1.4135. Min Act: -0.0001

Data Index: 523446 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 1.7000. Min Range: -1.7000

Max Act: 1.4944. Min Act: -0.0001

Data Index: 189400 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 1.7000. Min Range: -1.7000

Max Act: 1.3190. Min Act: -0.0001

Data Index: 1166794 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 1.7000. Min Range: -1.7000

Max Act: 1.4289. Min Act: -0.0001

Data Index: 1168464 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 1.7000. Min Range: -1.7000

Max Act: 1.3891. Min Act: -0.0001

Data Index: 641165 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 1.7000. Min Range: -1.7000

Max Act: 1.3594. Min Act: -0.0001

Data Index: 638577 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 1.7000. Min Range: -1.7000

Max Act: 1.2391. Min Act: -0.0001

Data Index: 166769 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 1.7000. Min Range: -1.7000

Max Act: 1.3302. Min Act: -0.0000

Data Index: 525114 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 1.7000. Min Range: -1.7000

Max Act: 1.3151. Min Act: -0.0001

Data Index: 563085 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 1.7000. Min Range: -1.7000

Max Act: 1.3518. Min Act: -0.0001

Data Index: 15593 (C4 (Web Text))

Max Activating Token Index: 149

Text #16

Max Range: 1.7000. Min Range: -1.7000

Max Act: 1.1889. Min Act: -0.0001

Data Index: 809819 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 1.7000. Min Range: -1.7000

Max Act: 1.3348. Min Act: -0.0001

Data Index: 1149428 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 1.7000. Min Range: -1.7000

Max Act: 1.2758. Min Act: -0.0001

Data Index: 1090886 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 1.7000. Min Range: -1.7000

Max Act: 1.3149. Min Act: -0.0001

Data Index: 929876 (C4 (Web Text))

Max Activating Token Index: 33