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

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

Neuron 3453 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.8419. Min Act: -0.0002

Data Index: 144162 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.6428. Min Act: -0.0002

Data Index: 1022166 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.6393. Min Act: -0.0002

Data Index: 786215 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.6690. Min Act: -0.0001

Data Index: 475195 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.6268. Min Act: -0.0001

Data Index: 66781 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.6165. Min Act: -0.0002

Data Index: 1154328 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.5898. Min Act: -0.0002

Data Index: 714004 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.6036. Min Act: -0.0002

Data Index: 762806 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.5866. Min Act: -0.0001

Data Index: 523814 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.5983. Min Act: -0.0002

Data Index: 1294296 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.6079. Min Act: -0.0002

Data Index: 1036883 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.5866. Min Act: -0.0002

Data Index: 1122967 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.5941. Min Act: -0.0002

Data Index: 234123 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.5557. Min Act: -0.0002

Data Index: 207734 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.5810. Min Act: -0.0001

Data Index: 1286764 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.5682. Min Act: -0.0001

Data Index: 459684 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.5540. Min Act: -0.0001

Data Index: 1304300 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.5577. Min Act: -0.0002

Data Index: 950233 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.5522. Min Act: -0.0002

Data Index: 87233 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.5678. Min Act: -0.0002

Data Index: 1068711 (C4 (Web Text))

Max Activating Token Index: 426