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

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

Neuron 535 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3502. Min Range: -1.3502

Max Act: 1.3502. Min Act: -0.0001

Data Index: 932325 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 1.3502. Min Range: -1.3502

Max Act: 1.1736. Min Act: -0.0001

Data Index: 632376 (C4 (Web Text))

Max Activating Token Index: 677

Text #2

Max Range: 1.3502. Min Range: -1.3502

Max Act: 1.1593. Min Act: -0.0001

Data Index: 1594443 (Python Code)

Max Activating Token Index: 31

Text #3

Max Range: 1.3502. Min Range: -1.3502

Max Act: 1.1091. Min Act: -0.0001

Data Index: 1250817 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 1.3502. Min Range: -1.3502

Max Act: 1.1339. Min Act: -0.0000

Data Index: 584469 (C4 (Web Text))

Max Activating Token Index: 212

Text #5

Max Range: 1.3502. Min Range: -1.3502

Max Act: 1.1087. Min Act: -0.0000

Data Index: 587980 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 1.3502. Min Range: -1.3502

Max Act: 1.1020. Min Act: -0.0000

Data Index: 121429 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 1.3502. Min Range: -1.3502

Max Act: 1.1322. Min Act: -0.0000

Data Index: 878644 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 1.3502. Min Range: -1.3502

Max Act: 1.0958. Min Act: -0.0001

Data Index: 1412661 (Python Code)

Max Activating Token Index: 857

Text #9

Max Range: 1.3502. Min Range: -1.3502

Max Act: 1.0489. Min Act: -0.0001

Data Index: 301832 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 1.3502. Min Range: -1.3502

Max Act: 1.0470. Min Act: -0.0000

Data Index: 1194863 (C4 (Web Text))

Max Activating Token Index: 277

Text #11

Max Range: 1.3502. Min Range: -1.3502

Max Act: 1.0191. Min Act: -0.0000

Data Index: 589487 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 1.3502. Min Range: -1.3502

Max Act: 0.9976. Min Act: -0.0000

Data Index: 1284745 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 1.3502. Min Range: -1.3502

Max Act: 1.0586. Min Act: -0.0000

Data Index: 48622 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 1.3502. Min Range: -1.3502

Max Act: 1.0269. Min Act: -0.0000

Data Index: 843074 (C4 (Web Text))

Max Activating Token Index: 212

Text #15

Max Range: 1.3502. Min Range: -1.3502

Max Act: 1.0191. Min Act: -0.0000

Data Index: 741853 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 1.3502. Min Range: -1.3502

Max Act: 1.0084. Min Act: -0.0000

Data Index: 513006 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 1.3502. Min Range: -1.3502

Max Act: 0.9657. Min Act: -0.0000

Data Index: 879730 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 1.3502. Min Range: -1.3502

Max Act: 1.0390. Min Act: -0.0000

Data Index: 810389 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 1.3502. Min Range: -1.3502

Max Act: 1.0472. Min Act: -0.0000

Data Index: 760954 (C4 (Web Text))

Max Activating Token Index: 66