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

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

Neuron 4553 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: 5.6442. Min Range: -5.6442

Max Act: 5.6442. Min Act: -0.0000

Data Index: 293373 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 5.6442. Min Range: -5.6442

Max Act: 4.3931. Min Act: -0.0000

Data Index: 765064 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 5.6442. Min Range: -5.6442

Max Act: 4.3290. Min Act: -0.0001

Data Index: 579198 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 5.6442. Min Range: -5.6442

Max Act: 3.9489. Min Act: -0.0000

Data Index: 673586 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 5.6442. Min Range: -5.6442

Max Act: 4.0674. Min Act: -0.0000

Data Index: 1153382 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 5.6442. Min Range: -5.6442

Max Act: 3.8160. Min Act: -0.0000

Data Index: 1205182 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 5.6442. Min Range: -5.6442

Max Act: 3.8612. Min Act: -0.0000

Data Index: 702358 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 5.6442. Min Range: -5.6442

Max Act: 3.6303. Min Act: -0.0000

Data Index: 822094 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 5.6442. Min Range: -5.6442

Max Act: 3.5660. Min Act: -0.0001

Data Index: 893679 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 5.6442. Min Range: -5.6442

Max Act: 3.4411. Min Act: -0.0001

Data Index: 1008487 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 5.6442. Min Range: -5.6442

Max Act: 3.5590. Min Act: -0.0001

Data Index: 150125 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 5.6442. Min Range: -5.6442

Max Act: 3.5464. Min Act: -0.0000

Data Index: 334961 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 5.6442. Min Range: -5.6442

Max Act: 3.5440. Min Act: -0.0000

Data Index: 409201 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 5.6442. Min Range: -5.6442

Max Act: 3.3492. Min Act: -0.0001

Data Index: 782529 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 5.6442. Min Range: -5.6442

Max Act: 3.3200. Min Act: -0.0000

Data Index: 384003 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 5.6442. Min Range: -5.6442

Max Act: 3.5897. Min Act: -0.0000

Data Index: 826555 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 5.6442. Min Range: -5.6442

Max Act: 3.8440. Min Act: -0.0000

Data Index: 416934 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 5.6442. Min Range: -5.6442

Max Act: 3.1241. Min Act: -0.0001

Data Index: 1057548 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 5.6442. Min Range: -5.6442

Max Act: 3.2575. Min Act: -0.0001

Data Index: 1165294 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 5.6442. Min Range: -5.6442

Max Act: 3.5077. Min Act: -0.0000

Data Index: 317197 (C4 (Web Text))

Max Activating Token Index: 529