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

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

Neuron 5071 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0700. Min Act: -0.0001

Data Index: 1437476 (Python Code)

Max Activating Token Index: 9

Text #1

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0495. Min Act: -0.0001

Data Index: 1559940 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0494. Min Act: -0.0001

Data Index: 1529828 (Python Code)

Max Activating Token Index: 172

Text #3

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0461. Min Act: -0.0001

Data Index: 1425784 (Python Code)

Max Activating Token Index: 457

Text #4

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0454. Min Act: -0.0001

Data Index: 1389248 (Python Code)

Max Activating Token Index: 25

Text #5

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0465. Min Act: -0.0001

Data Index: 1480511 (Python Code)

Max Activating Token Index: 369

Text #6

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0449. Min Act: -0.0002

Data Index: 1585964 (Python Code)

Max Activating Token Index: 520

Text #7

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0448. Min Act: -0.0001

Data Index: 1408682 (Python Code)

Max Activating Token Index: 688

Text #8

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0440. Min Act: -0.0001

Data Index: 1365659 (Python Code)

Max Activating Token Index: 625

Text #9

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0435. Min Act: -0.0001

Data Index: 1373087 (Python Code)

Max Activating Token Index: 407

Text #10

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0443. Min Act: -0.0001

Data Index: 1615873 (Python Code)

Max Activating Token Index: 85

Text #11

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0439. Min Act: -0.0001

Data Index: 1375595 (Python Code)

Max Activating Token Index: 492

Text #12

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0429. Min Act: -0.0001

Data Index: 1545486 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0433. Min Act: -0.0001

Data Index: 1618912 (Python Code)

Max Activating Token Index: 489

Text #14

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0432. Min Act: -0.0001

Data Index: 1399390 (Python Code)

Max Activating Token Index: 369

Text #15

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0434. Min Act: -0.0001

Data Index: 1368999 (Python Code)

Max Activating Token Index: 916

Text #16

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0436. Min Act: -0.0001

Data Index: 1368720 (Python Code)

Max Activating Token Index: 355

Text #17

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0424. Min Act: -0.0001

Data Index: 1569553 (Python Code)

Max Activating Token Index: 1021

Text #18

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0431. Min Act: -0.0001

Data Index: 1415695 (Python Code)

Max Activating Token Index: 492

Text #19

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0425. Min Act: -0.0001

Data Index: 1491752 (Python Code)

Max Activating Token Index: 277