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

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

Neuron 1077 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.4865. Min Act: -0.0000

Data Index: 1276190 (C4 (Web Text))

Max Activating Token Index: 190

Text #1

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3897. Min Act: -0.0000

Data Index: 397700 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.4060. Min Act: -0.0000

Data Index: 1043673 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3964. Min Act: -0.0001

Data Index: 333762 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3594. Min Act: -0.0001

Data Index: 705579 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3439. Min Act: -0.0001

Data Index: 362395 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3020. Min Act: -0.0001

Data Index: 1101408 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3265. Min Act: -0.0001

Data Index: 933095 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3407. Min Act: -0.0001

Data Index: 565274 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3247. Min Act: -0.0001

Data Index: 389084 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3251. Min Act: -0.0001

Data Index: 893063 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3209. Min Act: -0.0001

Data Index: 459396 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.2972. Min Act: -0.0001

Data Index: 451026 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3054. Min Act: -0.0001

Data Index: 92765 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3179. Min Act: -0.0001

Data Index: 518382 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3634. Min Act: 0.0000

Data Index: 615812 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3068. Min Act: -0.0001

Data Index: 65485 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3181. Min Act: -0.0001

Data Index: 1229447 (C4 (Web Text))

Max Activating Token Index: 903

Text #18

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.2923. Min Act: -0.0001

Data Index: 574826 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3223. Min Act: -0.0001

Data Index: 1262428 (C4 (Web Text))

Max Activating Token Index: 417