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

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

Neuron 3599 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.2457. Min Act: -0.0000

Data Index: 1524079 (Python Code)

Max Activating Token Index: 859

Text #1

Max Range: 3.2457. Min Range: -3.2457

Max Act: 2.6459. Min Act: -0.0000

Data Index: 1362638 (Python Code)

Max Activating Token Index: 895

Text #2

Max Range: 3.2457. Min Range: -3.2457

Max Act: 2.5129. Min Act: -0.0000

Data Index: 1634758 (Python Code)

Max Activating Token Index: 535

Text #3

Max Range: 3.2457. Min Range: -3.2457

Max Act: 2.3558. Min Act: -0.0000

Data Index: 1364428 (Python Code)

Max Activating Token Index: 80

Text #4

Max Range: 3.2457. Min Range: -3.2457

Max Act: 2.1879. Min Act: -0.0000

Data Index: 1652637 (Python Code)

Max Activating Token Index: 971

Text #5

Max Range: 3.2457. Min Range: -3.2457

Max Act: 2.1863. Min Act: -0.0000

Data Index: 1454028 (Python Code)

Max Activating Token Index: 193

Text #6

Max Range: 3.2457. Min Range: -3.2457

Max Act: 2.2518. Min Act: -0.0000

Data Index: 1544660 (Python Code)

Max Activating Token Index: 983

Text #7

Max Range: 3.2457. Min Range: -3.2457

Max Act: 2.2311. Min Act: -0.0000

Data Index: 1472921 (Python Code)

Max Activating Token Index: 933

Text #8

Max Range: 3.2457. Min Range: -3.2457

Max Act: 1.9009. Min Act: -0.0000

Data Index: 1489801 (Python Code)

Max Activating Token Index: 851

Text #9

Max Range: 3.2457. Min Range: -3.2457

Max Act: 1.9476. Min Act: -0.0000

Data Index: 1418558 (Python Code)

Max Activating Token Index: 884

Text #10

Max Range: 3.2457. Min Range: -3.2457

Max Act: 1.9615. Min Act: -0.0000

Data Index: 1522429 (Python Code)

Max Activating Token Index: 518

Text #11

Max Range: 3.2457. Min Range: -3.2457

Max Act: 1.9264. Min Act: -0.0000

Data Index: 1473059 (Python Code)

Max Activating Token Index: 770

Text #12

Max Range: 3.2457. Min Range: -3.2457

Max Act: 1.7108. Min Act: -0.0000

Data Index: 1534211 (Python Code)

Max Activating Token Index: 615

Text #13

Max Range: 3.2457. Min Range: -3.2457

Max Act: 1.6128. Min Act: -0.0000

Data Index: 1468422 (Python Code)

Max Activating Token Index: 802

Text #14

Max Range: 3.2457. Min Range: -3.2457

Max Act: 1.4070. Min Act: -0.0000

Data Index: 1450165 (Python Code)

Max Activating Token Index: 959

Text #15

Max Range: 3.2457. Min Range: -3.2457

Max Act: 1.7801. Min Act: -0.0000

Data Index: 1567426 (Python Code)

Max Activating Token Index: 147

Text #16

Max Range: 3.2457. Min Range: -3.2457

Max Act: 1.7177. Min Act: -0.0000

Data Index: 1371967 (Python Code)

Max Activating Token Index: 625

Text #17

Max Range: 3.2457. Min Range: -3.2457

Max Act: 1.6987. Min Act: -0.0000

Data Index: 1491400 (Python Code)

Max Activating Token Index: 942

Text #18

Max Range: 3.2457. Min Range: -3.2457

Max Act: 1.5923. Min Act: -0.0000

Data Index: 1401516 (Python Code)

Max Activating Token Index: 218

Text #19

Max Range: 3.2457. Min Range: -3.2457

Max Act: 1.4464. Min Act: -0.0000

Data Index: 447252 (C4 (Web Text))

Max Activating Token Index: 654