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

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

Neuron 3938 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: 1.0360. Min Range: -1.0360

Max Act: 1.0360. Min Act: -0.0001

Data Index: 229594 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.9020. Min Act: -0.0001

Data Index: 860953 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.8122. Min Act: -0.0001

Data Index: 1271332 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.8071. Min Act: -0.0001

Data Index: 1490160 (Python Code)

Max Activating Token Index: 370

Text #4

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.7825. Min Act: -0.0001

Data Index: 1396234 (Python Code)

Max Activating Token Index: 755

Text #5

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.7671. Min Act: -0.0001

Data Index: 1454868 (Python Code)

Max Activating Token Index: 1004

Text #6

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.8086. Min Act: -0.0001

Data Index: 365631 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.8020. Min Act: -0.0001

Data Index: 1008648 (C4 (Web Text))

Max Activating Token Index: 230

Text #8

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.7449. Min Act: -0.0001

Data Index: 95504 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.7644. Min Act: -0.0001

Data Index: 345503 (C4 (Web Text))

Max Activating Token Index: 914

Text #10

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.8563. Min Act: -0.0001

Data Index: 269194 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.7337. Min Act: -0.0001

Data Index: 926292 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.7420. Min Act: -0.0001

Data Index: 325747 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.7499. Min Act: -0.0001

Data Index: 118885 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.6849. Min Act: -0.0001

Data Index: 1450014 (Python Code)

Max Activating Token Index: 548

Text #15

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.6705. Min Act: -0.0001

Data Index: 1453923 (Python Code)

Max Activating Token Index: 248

Text #16

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.6963. Min Act: -0.0001

Data Index: 1146408 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.6963. Min Act: -0.0001

Data Index: 1123382 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.6926. Min Act: -0.0001

Data Index: 117707 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.6934. Min Act: -0.0001

Data Index: 623246 (C4 (Web Text))

Max Activating Token Index: 382