Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1977 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9601. Min Range: -0.9601

Max Act: 0.9601. Min Act: -0.0001

Data Index: 1619361 (Python Code)

Max Activating Token Index: 663

Text #1

Max Range: 0.9601. Min Range: -0.9601

Max Act: 0.9108. Min Act: -0.0001

Data Index: 1583183 (Python Code)

Max Activating Token Index: 114

Text #2

Max Range: 0.9601. Min Range: -0.9601

Max Act: 0.8932. Min Act: -0.0001

Data Index: 1597572 (Python Code)

Max Activating Token Index: 111

Text #3

Max Range: 0.9601. Min Range: -0.9601

Max Act: 0.8877. Min Act: -0.0001

Data Index: 661608 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 0.9601. Min Range: -0.9601

Max Act: 0.8603. Min Act: -0.0001

Data Index: 1490964 (Python Code)

Max Activating Token Index: 590

Text #5

Max Range: 0.9601. Min Range: -0.9601

Max Act: 0.8565. Min Act: -0.0001

Data Index: 1392659 (Python Code)

Max Activating Token Index: 545

Text #6

Max Range: 0.9601. Min Range: -0.9601

Max Act: 0.8180. Min Act: -0.0001

Data Index: 1498804 (Python Code)

Max Activating Token Index: 456

Text #7

Max Range: 0.9601. Min Range: -0.9601

Max Act: 0.7874. Min Act: -0.0001

Data Index: 1376049 (Python Code)

Max Activating Token Index: 764

Text #8

Max Range: 0.9601. Min Range: -0.9601

Max Act: 0.8513. Min Act: -0.0001

Data Index: 1586178 (Python Code)

Max Activating Token Index: 883

Text #9

Max Range: 0.9601. Min Range: -0.9601

Max Act: 0.7937. Min Act: -0.0001

Data Index: 1384433 (Python Code)

Max Activating Token Index: 231

Text #10

Max Range: 0.9601. Min Range: -0.9601

Max Act: 0.7494. Min Act: -0.0001

Data Index: 1398798 (Python Code)

Max Activating Token Index: 776

Text #11

Max Range: 0.9601. Min Range: -0.9601

Max Act: 0.7878. Min Act: -0.0001

Data Index: 1364246 (Python Code)

Max Activating Token Index: 92

Text #12

Max Range: 0.9601. Min Range: -0.9601

Max Act: 0.6951. Min Act: -0.0001

Data Index: 1633516 (Python Code)

Max Activating Token Index: 621

Text #13

Max Range: 0.9601. Min Range: -0.9601

Max Act: 0.7878. Min Act: -0.0001

Data Index: 1494141 (Python Code)

Max Activating Token Index: 112

Text #14

Max Range: 0.9601. Min Range: -0.9601

Max Act: 0.7783. Min Act: -0.0000

Data Index: 1630616 (Python Code)

Max Activating Token Index: 430

Text #15

Max Range: 0.9601. Min Range: -0.9601

Max Act: 0.7270. Min Act: -0.0001

Data Index: 1420577 (Python Code)

Max Activating Token Index: 534

Text #16

Max Range: 0.9601. Min Range: -0.9601

Max Act: 0.7450. Min Act: -0.0001

Data Index: 1649651 (Python Code)

Max Activating Token Index: 826

Text #17

Max Range: 0.9601. Min Range: -0.9601

Max Act: 0.8197. Min Act: -0.0001

Data Index: 1648103 (Python Code)

Max Activating Token Index: 845

Text #18

Max Range: 0.9601. Min Range: -0.9601

Max Act: 0.7444. Min Act: -0.0001

Data Index: 1480429 (Python Code)

Max Activating Token Index: 753

Text #19

Max Range: 0.9601. Min Range: -0.9601

Max Act: 0.7950. Min Act: -0.0001

Data Index: 1369500 (Python Code)

Max Activating Token Index: 582