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

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

Neuron 3280 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: 2.7324. Min Range: -2.7324

Max Act: 2.7324. Min Act: -0.0000

Data Index: 13859 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 2.7324. Min Range: -2.7324

Max Act: 2.5840. Min Act: -0.0000

Data Index: 1482254 (Python Code)

Max Activating Token Index: 192

Text #2

Max Range: 2.7324. Min Range: -2.7324

Max Act: 2.5800. Min Act: -0.0000

Data Index: 1430476 (Python Code)

Max Activating Token Index: 606

Text #3

Max Range: 2.7324. Min Range: -2.7324

Max Act: 2.5012. Min Act: -0.0000

Data Index: 542414 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 2.7324. Min Range: -2.7324

Max Act: 2.5202. Min Act: -0.0000

Data Index: 690475 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 2.7324. Min Range: -2.7324

Max Act: 2.3926. Min Act: -0.0000

Data Index: 13592 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 2.7324. Min Range: -2.7324

Max Act: 2.4551. Min Act: -0.0000

Data Index: 369991 (C4 (Web Text))

Max Activating Token Index: 780

Text #7

Max Range: 2.7324. Min Range: -2.7324

Max Act: 2.5362. Min Act: -0.0000

Data Index: 107668 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 2.7324. Min Range: -2.7324

Max Act: 2.3727. Min Act: -0.0000

Data Index: 431878 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 2.7324. Min Range: -2.7324

Max Act: 2.2544. Min Act: -0.0000

Data Index: 1431224 (Python Code)

Max Activating Token Index: 940

Text #10

Max Range: 2.7324. Min Range: -2.7324

Max Act: 2.3552. Min Act: -0.0000

Data Index: 1400071 (Python Code)

Max Activating Token Index: 1001

Text #11

Max Range: 2.7324. Min Range: -2.7324

Max Act: 2.2586. Min Act: -0.0000

Data Index: 560904 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 2.7324. Min Range: -2.7324

Max Act: 2.3764. Min Act: -0.0000

Data Index: 1152836 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 2.7324. Min Range: -2.7324

Max Act: 2.2572. Min Act: -0.0000

Data Index: 721459 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 2.7324. Min Range: -2.7324

Max Act: 2.3592. Min Act: -0.0000

Data Index: 230079 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 2.7324. Min Range: -2.7324

Max Act: 2.3161. Min Act: -0.0000

Data Index: 276793 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 2.7324. Min Range: -2.7324

Max Act: 2.2898. Min Act: -0.0000

Data Index: 1513604 (Python Code)

Max Activating Token Index: 456

Text #17

Max Range: 2.7324. Min Range: -2.7324

Max Act: 2.2764. Min Act: -0.0000

Data Index: 874064 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 2.7324. Min Range: -2.7324

Max Act: 2.2787. Min Act: -0.0000

Data Index: 998446 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 2.7324. Min Range: -2.7324

Max Act: 2.3556. Min Act: -0.0000

Data Index: 333474 (C4 (Web Text))

Max Activating Token Index: 78