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

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

Neuron 2550 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: 0.0687. Min Range: -0.0687

Max Act: 0.0687. Min Act: -0.0000

Data Index: 1198198 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0581. Min Act: -0.0000

Data Index: 1594090 (Python Code)

Max Activating Token Index: 514

Text #2

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0538. Min Act: -0.0000

Data Index: 1574981 (Python Code)

Max Activating Token Index: 363

Text #3

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0519. Min Act: -0.0000

Data Index: 1596928 (Python Code)

Max Activating Token Index: 490

Text #4

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0568. Min Act: -0.0000

Data Index: 1625776 (Python Code)

Max Activating Token Index: 565

Text #5

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0574. Min Act: -0.0000

Data Index: 1644949 (Python Code)

Max Activating Token Index: 805

Text #6

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0531. Min Act: -0.0000

Data Index: 1568943 (Python Code)

Max Activating Token Index: 420

Text #7

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0506. Min Act: -0.0000

Data Index: 1020162 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0527. Min Act: -0.0000

Data Index: 1414955 (Python Code)

Max Activating Token Index: 555

Text #9

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0476. Min Act: -0.0000

Data Index: 1367959 (Python Code)

Max Activating Token Index: 805

Text #10

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0451. Min Act: -0.0000

Data Index: 1394272 (Python Code)

Max Activating Token Index: 579

Text #11

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0459. Min Act: -0.0000

Data Index: 1465051 (Python Code)

Max Activating Token Index: 927

Text #12

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0481. Min Act: -0.0000

Data Index: 1577659 (Python Code)

Max Activating Token Index: 471

Text #13

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0423. Min Act: -0.0000

Data Index: 1370257 (Python Code)

Max Activating Token Index: 606

Text #14

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0438. Min Act: -0.0000

Data Index: 284629 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0460. Min Act: -0.0000

Data Index: 1447559 (Python Code)

Max Activating Token Index: 488

Text #16

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0452. Min Act: -0.0000

Data Index: 1647204 (Python Code)

Max Activating Token Index: 548

Text #17

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0395. Min Act: -0.0000

Data Index: 1544341 (Python Code)

Max Activating Token Index: 924

Text #18

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0456. Min Act: -0.0000

Data Index: 1529263 (Python Code)

Max Activating Token Index: 916

Text #19

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0453. Min Act: -0.0000

Data Index: 1183924 (C4 (Web Text))

Max Activating Token Index: 349