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

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

Neuron 5347 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: 1.3861. Min Range: -1.3861

Max Act: 1.3861. Min Act: -0.0000

Data Index: 1044896 (C4 (Web Text))

Max Activating Token Index: 859

Text #1

Max Range: 1.3861. Min Range: -1.3861

Max Act: 1.3840. Min Act: -0.0000

Data Index: 873723 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 1.3861. Min Range: -1.3861

Max Act: 1.2646. Min Act: 0.0000

Data Index: 136280 (C4 (Web Text))

Max Activating Token Index: 521

Text #3

Max Range: 1.3861. Min Range: -1.3861

Max Act: 1.0674. Min Act: -0.0000

Data Index: 603982 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 1.3861. Min Range: -1.3861

Max Act: 1.0451. Min Act: 0.0001

Data Index: 695645 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 1.3861. Min Range: -1.3861

Max Act: 1.0181. Min Act: -0.0000

Data Index: 233925 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 1.3861. Min Range: -1.3861

Max Act: 1.0016. Min Act: -0.0000

Data Index: 1258494 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 1.3861. Min Range: -1.3861

Max Act: 1.0658. Min Act: -0.0000

Data Index: 1061786 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 1.3861. Min Range: -1.3861

Max Act: 0.9405. Min Act: -0.0000

Data Index: 1347898 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 1.3861. Min Range: -1.3861

Max Act: 0.9063. Min Act: -0.0000

Data Index: 194835 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 1.3861. Min Range: -1.3861

Max Act: 0.9560. Min Act: -0.0000

Data Index: 200836 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 1.3861. Min Range: -1.3861

Max Act: 1.0538. Min Act: -0.0000

Data Index: 57213 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 1.3861. Min Range: -1.3861

Max Act: 0.8021. Min Act: -0.0000

Data Index: 267713 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 1.3861. Min Range: -1.3861

Max Act: 0.8192. Min Act: -0.0000

Data Index: 1230693 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 1.3861. Min Range: -1.3861

Max Act: 0.7891. Min Act: -0.0000

Data Index: 87981 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 1.3861. Min Range: -1.3861

Max Act: 0.8337. Min Act: -0.0000

Data Index: 859024 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 1.3861. Min Range: -1.3861

Max Act: 0.8102. Min Act: 0.0000

Data Index: 677248 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 1.3861. Min Range: -1.3861

Max Act: 0.7769. Min Act: -0.0000

Data Index: 268540 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 1.3861. Min Range: -1.3861

Max Act: 0.8235. Min Act: -0.0000

Data Index: 242259 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 1.3861. Min Range: -1.3861

Max Act: 0.7669. Min Act: -0.0000

Data Index: 57215 (C4 (Web Text))

Max Activating Token Index: 650