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

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

Neuron 229 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: 0.1082. Min Range: -0.1082

Max Act: 0.1082. Min Act: -0.0001

Data Index: 1480775 (Python Code)

Max Activating Token Index: 774

Text #1

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0650. Min Act: -0.0001

Data Index: 1499383 (Python Code)

Max Activating Token Index: 965

Text #2

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0634. Min Act: -0.0001

Data Index: 1506450 (Python Code)

Max Activating Token Index: 672

Text #3

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0673. Min Act: -0.0001

Data Index: 1361503 (Python Code)

Max Activating Token Index: 762

Text #4

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0616. Min Act: -0.0001

Data Index: 1516091 (Python Code)

Max Activating Token Index: 605

Text #5

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0601. Min Act: -0.0001

Data Index: 1619489 (Python Code)

Max Activating Token Index: 534

Text #6

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0587. Min Act: -0.0001

Data Index: 1593792 (Python Code)

Max Activating Token Index: 1009

Text #7

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0609. Min Act: -0.0001

Data Index: 1626792 (Python Code)

Max Activating Token Index: 908

Text #8

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0554. Min Act: -0.0001

Data Index: 1648814 (Python Code)

Max Activating Token Index: 806

Text #9

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0595. Min Act: -0.0001

Data Index: 1639167 (Python Code)

Max Activating Token Index: 831

Text #10

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0525. Min Act: -0.0001

Data Index: 1383910 (Python Code)

Max Activating Token Index: 965

Text #11

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0555. Min Act: -0.0001

Data Index: 1505324 (Python Code)

Max Activating Token Index: 900

Text #12

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0540. Min Act: -0.0001

Data Index: 1654856 (Python Code)

Max Activating Token Index: 766

Text #13

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0551. Min Act: -0.0001

Data Index: 1571364 (Python Code)

Max Activating Token Index: 900

Text #14

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0529. Min Act: -0.0001

Data Index: 1535993 (Python Code)

Max Activating Token Index: 841

Text #15

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0483. Min Act: -0.0001

Data Index: 1534710 (Python Code)

Max Activating Token Index: 958

Text #16

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0544. Min Act: -0.0001

Data Index: 1407844 (Python Code)

Max Activating Token Index: 928

Text #17

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0565. Min Act: -0.0001

Data Index: 1501720 (Python Code)

Max Activating Token Index: 731

Text #18

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0544. Min Act: -0.0001

Data Index: 1600166 (Python Code)

Max Activating Token Index: 771

Text #19

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0538. Min Act: -0.0001

Data Index: 1496308 (Python Code)

Max Activating Token Index: 609