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

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

Neuron 3437 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.5085. Min Act: -0.0000

Data Index: 1397817 (Python Code)

Max Activating Token Index: 606

Text #1

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.3773. Min Act: -0.0000

Data Index: 1583896 (Python Code)

Max Activating Token Index: 925

Text #2

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.3371. Min Act: -0.0000

Data Index: 1553424 (Python Code)

Max Activating Token Index: 889

Text #3

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.2666. Min Act: -0.0000

Data Index: 1514632 (Python Code)

Max Activating Token Index: 723

Text #4

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.2633. Min Act: -0.0000

Data Index: 1397051 (Python Code)

Max Activating Token Index: 468

Text #5

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.2756. Min Act: -0.0000

Data Index: 1502022 (Python Code)

Max Activating Token Index: 65

Text #6

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.2389. Min Act: -0.0000

Data Index: 1544153 (Python Code)

Max Activating Token Index: 943

Text #7

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.2272. Min Act: -0.0000

Data Index: 1613915 (Python Code)

Max Activating Token Index: 783

Text #8

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.2246. Min Act: -0.0000

Data Index: 1443215 (Python Code)

Max Activating Token Index: 895

Text #9

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.2093. Min Act: -0.0000

Data Index: 1561969 (Python Code)

Max Activating Token Index: 886

Text #10

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.2101. Min Act: -0.0000

Data Index: 1423731 (Python Code)

Max Activating Token Index: 980

Text #11

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.2066. Min Act: -0.0000

Data Index: 1362763 (Python Code)

Max Activating Token Index: 591

Text #12

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.1972. Min Act: -0.0000

Data Index: 1595942 (Python Code)

Max Activating Token Index: 497

Text #13

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.2019. Min Act: -0.0000

Data Index: 1594228 (Python Code)

Max Activating Token Index: 552

Text #14

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.2070. Min Act: -0.0000

Data Index: 1573839 (Python Code)

Max Activating Token Index: 776

Text #15

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.1850. Min Act: -0.0000

Data Index: 1526008 (Python Code)

Max Activating Token Index: 341

Text #16

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.1875. Min Act: -0.0000

Data Index: 1466610 (Python Code)

Max Activating Token Index: 819

Text #17

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.1762. Min Act: -0.0000

Data Index: 1534776 (Python Code)

Max Activating Token Index: 218

Text #18

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.1909. Min Act: -0.0000

Data Index: 1519903 (Python Code)

Max Activating Token Index: 920

Text #19

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.2075. Min Act: -0.0000

Data Index: 1599990 (Python Code)

Max Activating Token Index: 340