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

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

Neuron 1811 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: 2.4037. Min Range: -2.4037

Max Act: 2.2810. Min Act: -0.0000

Data Index: 1183865 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 2.4037. Min Range: -2.4037

Max Act: 2.2848. Min Act: -0.0000

Data Index: 336463 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 2.4037. Min Range: -2.4037

Max Act: 2.2731. Min Act: -0.0000

Data Index: 1241079 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 2.4037. Min Range: -2.4037

Max Act: 2.4037. Min Act: -0.0000

Data Index: 134654 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 2.4037. Min Range: -2.4037

Max Act: 2.1831. Min Act: -0.0000

Data Index: 610247 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 2.4037. Min Range: -2.4037

Max Act: 2.2821. Min Act: -0.0000

Data Index: 430152 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 2.4037. Min Range: -2.4037

Max Act: 2.2531. Min Act: -0.0000

Data Index: 872253 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 2.4037. Min Range: -2.4037

Max Act: 2.1668. Min Act: -0.0000

Data Index: 323090 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 2.4037. Min Range: -2.4037

Max Act: 1.9717. Min Act: -0.0000

Data Index: 634462 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 2.4037. Min Range: -2.4037

Max Act: 1.9777. Min Act: -0.0000

Data Index: 1345122 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 2.4037. Min Range: -2.4037

Max Act: 2.0489. Min Act: -0.0000

Data Index: 315754 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 2.4037. Min Range: -2.4037

Max Act: 1.9123. Min Act: -0.0000

Data Index: 1169298 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 2.4037. Min Range: -2.4037

Max Act: 1.8064. Min Act: -0.0000

Data Index: 537896 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 2.4037. Min Range: -2.4037

Max Act: 1.9006. Min Act: -0.0000

Data Index: 55476 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 2.4037. Min Range: -2.4037

Max Act: 1.7786. Min Act: -0.0000

Data Index: 190700 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 2.4037. Min Range: -2.4037

Max Act: 1.9601. Min Act: -0.0000

Data Index: 1514783 (Python Code)

Max Activating Token Index: 471

Text #16

Max Range: 2.4037. Min Range: -2.4037

Max Act: 1.8375. Min Act: -0.0000

Data Index: 1513850 (Python Code)

Max Activating Token Index: 850

Text #17

Max Range: 2.4037. Min Range: -2.4037

Max Act: 1.9253. Min Act: -0.0000

Data Index: 1472410 (Python Code)

Max Activating Token Index: 966

Text #18

Max Range: 2.4037. Min Range: -2.4037

Max Act: 1.9108. Min Act: -0.0000

Data Index: 615136 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 2.4037. Min Range: -2.4037

Max Act: 1.8064. Min Act: -0.0000

Data Index: 539993 (C4 (Web Text))

Max Activating Token Index: 577