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

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

Neuron 3529 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2650. Min Range: -1.2650

Max Act: 1.2333. Min Act: -0.0000

Data Index: 1605694 (Python Code)

Max Activating Token Index: 366

Text #1

Max Range: 1.2650. Min Range: -1.2650

Max Act: 1.1514. Min Act: -0.0000

Data Index: 1404536 (Python Code)

Max Activating Token Index: 754

Text #2

Max Range: 1.2650. Min Range: -1.2650

Max Act: 1.1039. Min Act: -0.0000

Data Index: 1656227 (Python Code)

Max Activating Token Index: 299

Text #3

Max Range: 1.2650. Min Range: -1.2650

Max Act: 1.2650. Min Act: -0.0000

Data Index: 1365817 (Python Code)

Max Activating Token Index: 303

Text #4

Max Range: 1.2650. Min Range: -1.2650

Max Act: 1.1753. Min Act: -0.0000

Data Index: 599939 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 1.2650. Min Range: -1.2650

Max Act: 1.0694. Min Act: 0.0000

Data Index: 200410 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.9966. Min Act: 0.0000

Data Index: 299293 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.8972. Min Act: -0.0000

Data Index: 180166 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.9503. Min Act: 0.0000

Data Index: 444673 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 1.2650. Min Range: -1.2650

Max Act: 1.0228. Min Act: -0.0000

Data Index: 813939 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.8515. Min Act: 0.0000

Data Index: 590784 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.8588. Min Act: -0.0000

Data Index: 1292126 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.8580. Min Act: -0.0000

Data Index: 1635082 (Python Code)

Max Activating Token Index: 146

Text #13

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.8835. Min Act: -0.0000

Data Index: 544367 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.8472. Min Act: -0.0000

Data Index: 1240377 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.8569. Min Act: -0.0000

Data Index: 727402 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.8617. Min Act: 0.0000

Data Index: 518135 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.8550. Min Act: -0.0000

Data Index: 291983 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.8494. Min Act: -0.0000

Data Index: 906328 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.8366. Min Act: -0.0000

Data Index: 1003454 (C4 (Web Text))

Max Activating Token Index: 244