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

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

Neuron 3954 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.4625. Min Range: -6.4625

Max Act: 6.4625. Min Act: -0.0000

Data Index: 1422089 (Python Code)

Max Activating Token Index: 120

Text #1

Max Range: 6.4625. Min Range: -6.4625

Max Act: 6.1708. Min Act: -0.0000

Data Index: 1607574 (Python Code)

Max Activating Token Index: 708

Text #2

Max Range: 6.4625. Min Range: -6.4625

Max Act: 6.1123. Min Act: -0.0000

Data Index: 1632582 (Python Code)

Max Activating Token Index: 74

Text #3

Max Range: 6.4625. Min Range: -6.4625

Max Act: 6.2662. Min Act: -0.0000

Data Index: 1407099 (Python Code)

Max Activating Token Index: 50

Text #4

Max Range: 6.4625. Min Range: -6.4625

Max Act: 5.8742. Min Act: -0.0000

Data Index: 1377761 (Python Code)

Max Activating Token Index: 100

Text #5

Max Range: 6.4625. Min Range: -6.4625

Max Act: 6.0787. Min Act: -0.0000

Data Index: 1381454 (Python Code)

Max Activating Token Index: 109

Text #6

Max Range: 6.4625. Min Range: -6.4625

Max Act: 5.9254. Min Act: -0.0000

Data Index: 1636670 (Python Code)

Max Activating Token Index: 85

Text #7

Max Range: 6.4625. Min Range: -6.4625

Max Act: 5.7033. Min Act: -0.0000

Data Index: 1656852 (Python Code)

Max Activating Token Index: 9

Text #8

Max Range: 6.4625. Min Range: -6.4625

Max Act: 5.4919. Min Act: -0.0000

Data Index: 1453897 (Python Code)

Max Activating Token Index: 9

Text #9

Max Range: 6.4625. Min Range: -6.4625

Max Act: 5.6170. Min Act: -0.0000

Data Index: 1575267 (Python Code)

Max Activating Token Index: 747

Text #10

Max Range: 6.4625. Min Range: -6.4625

Max Act: 5.3724. Min Act: -0.0000

Data Index: 1497056 (Python Code)

Max Activating Token Index: 480

Text #11

Max Range: 6.4625. Min Range: -6.4625

Max Act: 5.2029. Min Act: -0.0000

Data Index: 1440377 (Python Code)

Max Activating Token Index: 410

Text #12

Max Range: 6.4625. Min Range: -6.4625

Max Act: 5.2739. Min Act: -0.0000

Data Index: 1392271 (Python Code)

Max Activating Token Index: 88

Text #13

Max Range: 6.4625. Min Range: -6.4625

Max Act: 5.5479. Min Act: -0.0000

Data Index: 1506496 (Python Code)

Max Activating Token Index: 994

Text #14

Max Range: 6.4625. Min Range: -6.4625

Max Act: 5.4984. Min Act: -0.0000

Data Index: 1535245 (Python Code)

Max Activating Token Index: 461

Text #15

Max Range: 6.4625. Min Range: -6.4625

Max Act: 5.2994. Min Act: -0.0000

Data Index: 1449583 (Python Code)

Max Activating Token Index: 47

Text #16

Max Range: 6.4625. Min Range: -6.4625

Max Act: 5.2527. Min Act: -0.0000

Data Index: 1435513 (Python Code)

Max Activating Token Index: 544

Text #17

Max Range: 6.4625. Min Range: -6.4625

Max Act: 5.2166. Min Act: -0.0000

Data Index: 1603446 (Python Code)

Max Activating Token Index: 231

Text #18

Max Range: 6.4625. Min Range: -6.4625

Max Act: 4.9824. Min Act: -0.0000

Data Index: 1555972 (Python Code)

Max Activating Token Index: 25

Text #19

Max Range: 6.4625. Min Range: -6.4625

Max Act: 4.9901. Min Act: -0.0000

Data Index: 1396121 (Python Code)

Max Activating Token Index: 134