Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1951 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.3106. Min Range: -4.3106

Max Act: 4.3106. Min Act: -0.0000

Data Index: 1456020 (Python Code)

Max Activating Token Index: 225

Text #1

Max Range: 4.3106. Min Range: -4.3106

Max Act: 3.2584. Min Act: -0.0000

Data Index: 1373776 (Python Code)

Max Activating Token Index: 860

Text #2

Max Range: 4.3106. Min Range: -4.3106

Max Act: 2.4505. Min Act: -0.0000

Data Index: 1548960 (Python Code)

Max Activating Token Index: 842

Text #3

Max Range: 4.3106. Min Range: -4.3106

Max Act: 2.1849. Min Act: -0.0000

Data Index: 1571194 (Python Code)

Max Activating Token Index: 982

Text #4

Max Range: 4.3106. Min Range: -4.3106

Max Act: 1.8809. Min Act: -0.0000

Data Index: 1580738 (Python Code)

Max Activating Token Index: 662

Text #5

Max Range: 4.3106. Min Range: -4.3106

Max Act: 2.0753. Min Act: -0.0000

Data Index: 1504394 (Python Code)

Max Activating Token Index: 484

Text #6

Max Range: 4.3106. Min Range: -4.3106

Max Act: 1.9717. Min Act: -0.0000

Data Index: 1385273 (Python Code)

Max Activating Token Index: 926

Text #7

Max Range: 4.3106. Min Range: -4.3106

Max Act: 1.6274. Min Act: -0.0000

Data Index: 1494089 (Python Code)

Max Activating Token Index: 320

Text #8

Max Range: 4.3106. Min Range: -4.3106

Max Act: 1.7277. Min Act: -0.0000

Data Index: 1639567 (Python Code)

Max Activating Token Index: 287

Text #9

Max Range: 4.3106. Min Range: -4.3106

Max Act: 1.6250. Min Act: -0.0000

Data Index: 1450881 (Python Code)

Max Activating Token Index: 999

Text #10

Max Range: 4.3106. Min Range: -4.3106

Max Act: 1.6545. Min Act: -0.0000

Data Index: 1433180 (Python Code)

Max Activating Token Index: 33

Text #11

Max Range: 4.3106. Min Range: -4.3106

Max Act: 1.8322. Min Act: -0.0000

Data Index: 1626440 (Python Code)

Max Activating Token Index: 398

Text #12

Max Range: 4.3106. Min Range: -4.3106

Max Act: 1.8460. Min Act: -0.0000

Data Index: 1515596 (Python Code)

Max Activating Token Index: 594

Text #13

Max Range: 4.3106. Min Range: -4.3106

Max Act: 1.6330. Min Act: -0.0000

Data Index: 1514656 (Python Code)

Max Activating Token Index: 297

Text #14

Max Range: 4.3106. Min Range: -4.3106

Max Act: 1.5652. Min Act: -0.0000

Data Index: 1578393 (Python Code)

Max Activating Token Index: 812

Text #15

Max Range: 4.3106. Min Range: -4.3106

Max Act: 1.4963. Min Act: -0.0000

Data Index: 1500724 (Python Code)

Max Activating Token Index: 932

Text #16

Max Range: 4.3106. Min Range: -4.3106

Max Act: 1.4310. Min Act: -0.0000

Data Index: 1538312 (Python Code)

Max Activating Token Index: 395

Text #17

Max Range: 4.3106. Min Range: -4.3106

Max Act: 1.3965. Min Act: -0.0000

Data Index: 1526147 (Python Code)

Max Activating Token Index: 999

Text #18

Max Range: 4.3106. Min Range: -4.3106

Max Act: 1.1091. Min Act: -0.0000

Data Index: 1364481 (Python Code)

Max Activating Token Index: 825

Text #19

Max Range: 4.3106. Min Range: -4.3106

Max Act: 1.4056. Min Act: -0.0000

Data Index: 1586283 (Python Code)

Max Activating Token Index: 581