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

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

Neuron 4290 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.4099. Min Act: -0.0000

Data Index: 1433945 (Python Code)

Max Activating Token Index: 377

Text #1

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.4077. Min Act: -0.0000

Data Index: 1432536 (Python Code)

Max Activating Token Index: 209

Text #2

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3607. Min Act: -0.0000

Data Index: 1422151 (Python Code)

Max Activating Token Index: 10

Text #3

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3814. Min Act: -0.0000

Data Index: 1628306 (Python Code)

Max Activating Token Index: 484

Text #4

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3693. Min Act: -0.0000

Data Index: 1581246 (Python Code)

Max Activating Token Index: 704

Text #5

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3420. Min Act: -0.0001

Data Index: 1448639 (Python Code)

Max Activating Token Index: 441

Text #6

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3461. Min Act: -0.0000

Data Index: 1466651 (Python Code)

Max Activating Token Index: 117

Text #7

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3580. Min Act: -0.0000

Data Index: 1581850 (Python Code)

Max Activating Token Index: 266

Text #8

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3545. Min Act: -0.0000

Data Index: 1490334 (Python Code)

Max Activating Token Index: 555

Text #9

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3437. Min Act: -0.0000

Data Index: 1549571 (Python Code)

Max Activating Token Index: 88

Text #10

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3294. Min Act: -0.0000

Data Index: 1651750 (Python Code)

Max Activating Token Index: 863

Text #11

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3506. Min Act: -0.0000

Data Index: 1505390 (Python Code)

Max Activating Token Index: 802

Text #12

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3496. Min Act: -0.0001

Data Index: 1586995 (Python Code)

Max Activating Token Index: 456

Text #13

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3422. Min Act: -0.0000

Data Index: 1517939 (Python Code)

Max Activating Token Index: 614

Text #14

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3681. Min Act: -0.0000

Data Index: 1636320 (Python Code)

Max Activating Token Index: 1000

Text #15

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3177. Min Act: -0.0000

Data Index: 1469528 (Python Code)

Max Activating Token Index: 621

Text #16

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3178. Min Act: -0.0000

Data Index: 1600739 (Python Code)

Max Activating Token Index: 688

Text #17

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3282. Min Act: -0.0000

Data Index: 1588454 (Python Code)

Max Activating Token Index: 97

Text #18

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3487. Min Act: -0.0001

Data Index: 1384288 (Python Code)

Max Activating Token Index: 77

Text #19

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3253. Min Act: -0.0000

Data Index: 1605498 (Python Code)

Max Activating Token Index: 496