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

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

Neuron 5382 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: 2.8844. Min Range: -2.8844

Max Act: 2.7116. Min Act: -0.0000

Data Index: 1590104 (Python Code)

Max Activating Token Index: 252

Text #1

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.6761. Min Act: -0.0000

Data Index: 1367128 (Python Code)

Max Activating Token Index: 79

Text #2

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.7996. Min Act: -0.0000

Data Index: 1615704 (Python Code)

Max Activating Token Index: 510

Text #3

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.8844. Min Act: -0.0000

Data Index: 1626424 (Python Code)

Max Activating Token Index: 723

Text #4

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.5761. Min Act: -0.0000

Data Index: 1518886 (Python Code)

Max Activating Token Index: 258

Text #5

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.5806. Min Act: -0.0000

Data Index: 1435968 (Python Code)

Max Activating Token Index: 471

Text #6

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.4410. Min Act: -0.0000

Data Index: 1592348 (Python Code)

Max Activating Token Index: 112

Text #7

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.4096. Min Act: -0.0000

Data Index: 1467337 (Python Code)

Max Activating Token Index: 312

Text #8

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.3625. Min Act: -0.0000

Data Index: 1571462 (Python Code)

Max Activating Token Index: 849

Text #9

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.3196. Min Act: -0.0000

Data Index: 790010 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.1533. Min Act: -0.0000

Data Index: 1497074 (Python Code)

Max Activating Token Index: 914

Text #11

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.2653. Min Act: -0.0000

Data Index: 1462506 (Python Code)

Max Activating Token Index: 893

Text #12

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.3374. Min Act: -0.0000

Data Index: 1530163 (Python Code)

Max Activating Token Index: 758

Text #13

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.2448. Min Act: -0.0000

Data Index: 1486724 (Python Code)

Max Activating Token Index: 330

Text #14

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.0970. Min Act: -0.0000

Data Index: 1523103 (Python Code)

Max Activating Token Index: 719

Text #15

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.2778. Min Act: -0.0000

Data Index: 1464408 (Python Code)

Max Activating Token Index: 175

Text #16

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.1177. Min Act: -0.0000

Data Index: 37848 (C4 (Web Text))

Max Activating Token Index: 929

Text #17

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.2447. Min Act: -0.0000

Data Index: 360615 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.1143. Min Act: -0.0000

Data Index: 1429135 (Python Code)

Max Activating Token Index: 131

Text #19

Max Range: 2.8844. Min Range: -2.8844

Max Act: 1.9977. Min Act: -0.0000

Data Index: 1510762 (Python Code)

Max Activating Token Index: 60