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

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

Neuron 3573 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.4612. Min Act: -0.0001

Data Index: 1446419 (Python Code)

Max Activating Token Index: 675

Text #1

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.4475. Min Act: -0.0001

Data Index: 880594 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.3724. Min Act: -0.0001

Data Index: 581721 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.3913. Min Act: -0.0001

Data Index: 1478092 (Python Code)

Max Activating Token Index: 432

Text #4

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.3587. Min Act: -0.0001

Data Index: 1370432 (Python Code)

Max Activating Token Index: 103

Text #5

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.3916. Min Act: -0.0001

Data Index: 951767 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.3929. Min Act: -0.0001

Data Index: 1561904 (Python Code)

Max Activating Token Index: 160

Text #7

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.3055. Min Act: -0.0001

Data Index: 965134 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.3379. Min Act: -0.0001

Data Index: 1597790 (Python Code)

Max Activating Token Index: 52

Text #9

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.3322. Min Act: -0.0001

Data Index: 801017 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.3171. Min Act: -0.0001

Data Index: 1407878 (Python Code)

Max Activating Token Index: 388

Text #11

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.3092. Min Act: -0.0001

Data Index: 1530483 (Python Code)

Max Activating Token Index: 98

Text #12

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.3351. Min Act: -0.0001

Data Index: 528613 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.2843. Min Act: -0.0001

Data Index: 903593 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.2751. Min Act: -0.0001

Data Index: 1012879 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.3502. Min Act: -0.0001

Data Index: 371365 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.2330. Min Act: -0.0001

Data Index: 1424385 (Python Code)

Max Activating Token Index: 198

Text #17

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.2690. Min Act: -0.0001

Data Index: 1210999 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.3300. Min Act: -0.0001

Data Index: 185972 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.2662. Min Act: -0.0001

Data Index: 1260753 (C4 (Web Text))

Max Activating Token Index: 690