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

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

Neuron 3881 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: 0.7414. Min Range: -0.7414

Max Act: 0.7279. Min Act: -0.0000

Data Index: 1652033 (Python Code)

Max Activating Token Index: 215

Text #1

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.7414. Min Act: -0.0001

Data Index: 1559382 (Python Code)

Max Activating Token Index: 299

Text #2

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.7162. Min Act: -0.0000

Data Index: 1570684 (Python Code)

Max Activating Token Index: 691

Text #3

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.6973. Min Act: -0.0001

Data Index: 1462311 (Python Code)

Max Activating Token Index: 817

Text #4

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.6891. Min Act: -0.0000

Data Index: 1613102 (Python Code)

Max Activating Token Index: 334

Text #5

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.6709. Min Act: -0.0001

Data Index: 1478058 (Python Code)

Max Activating Token Index: 865

Text #6

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.6790. Min Act: -0.0001

Data Index: 1373509 (Python Code)

Max Activating Token Index: 271

Text #7

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.6703. Min Act: -0.0000

Data Index: 1609244 (Python Code)

Max Activating Token Index: 615

Text #8

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.6577. Min Act: -0.0001

Data Index: 1427805 (Python Code)

Max Activating Token Index: 507

Text #9

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.6326. Min Act: -0.0001

Data Index: 1579965 (Python Code)

Max Activating Token Index: 157

Text #10

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.6265. Min Act: -0.0001

Data Index: 1650021 (Python Code)

Max Activating Token Index: 799

Text #11

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.6246. Min Act: -0.0000

Data Index: 1474487 (Python Code)

Max Activating Token Index: 341

Text #12

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.6206. Min Act: -0.0000

Data Index: 1426449 (Python Code)

Max Activating Token Index: 985

Text #13

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.6070. Min Act: -0.0001

Data Index: 1523949 (Python Code)

Max Activating Token Index: 786

Text #14

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.6069. Min Act: -0.0001

Data Index: 1390921 (Python Code)

Max Activating Token Index: 471

Text #15

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.5835. Min Act: -0.0000

Data Index: 1608411 (Python Code)

Max Activating Token Index: 202

Text #16

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.6240. Min Act: -0.0001

Data Index: 1588684 (Python Code)

Max Activating Token Index: 301

Text #17

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.5825. Min Act: -0.0001

Data Index: 1404194 (Python Code)

Max Activating Token Index: 752

Text #18

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.6010. Min Act: -0.0001

Data Index: 1410117 (Python Code)

Max Activating Token Index: 452

Text #19

Max Range: 0.7414. Min Range: -0.7414

Max Act: 0.6044. Min Act: -0.0000

Data Index: 1586967 (Python Code)

Max Activating Token Index: 708