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

Dataset: The Pile

Neuron 2884 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.8768. Min Act: -0.0000

Data Index: 146200 (The Pile)

Max Activating Token Index: 233

Text #1

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.8814. Min Act: -0.0000

Data Index: 1072229 (The Pile)

Max Activating Token Index: 54

Text #2

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.8667. Min Act: -0.0000

Data Index: 1428499 (The Pile)

Max Activating Token Index: 894

Text #3

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.8273. Min Act: -0.0000

Data Index: 498331 (The Pile)

Max Activating Token Index: 452

Text #4

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.8452. Min Act: -0.0000

Data Index: 32694 (The Pile)

Max Activating Token Index: 651

Text #5

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.8944. Min Act: -0.0000

Data Index: 452355 (The Pile)

Max Activating Token Index: 879

Text #6

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.8582. Min Act: -0.0000

Data Index: 1431958 (The Pile)

Max Activating Token Index: 768

Text #7

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.9209. Min Act: -0.0000

Data Index: 359439 (The Pile)

Max Activating Token Index: 683

Text #8

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.7727. Min Act: -0.0000

Data Index: 1473438 (The Pile)

Max Activating Token Index: 650

Text #9

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.8245. Min Act: -0.0000

Data Index: 1461640 (The Pile)

Max Activating Token Index: 42

Text #10

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.7496. Min Act: -0.0000

Data Index: 502225 (The Pile)

Max Activating Token Index: 810

Text #11

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.8054. Min Act: -0.0000

Data Index: 1948602 (The Pile)

Max Activating Token Index: 786

Text #12

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.8911. Min Act: -0.0000

Data Index: 777522 (The Pile)

Max Activating Token Index: 219

Text #13

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.7709. Min Act: -0.0000

Data Index: 425831 (The Pile)

Max Activating Token Index: 318

Text #14

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.6886. Min Act: -0.0000

Data Index: 1384669 (The Pile)

Max Activating Token Index: 109

Text #15

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.7259. Min Act: -0.0000

Data Index: 411607 (The Pile)

Max Activating Token Index: 59

Text #16

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.6528. Min Act: -0.0000

Data Index: 1068595 (The Pile)

Max Activating Token Index: 865

Text #17

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.7017. Min Act: -0.0000

Data Index: 858802 (The Pile)

Max Activating Token Index: 8

Text #18

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.7569. Min Act: -0.0000

Data Index: 563264 (The Pile)

Max Activating Token Index: 40

Text #19

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.7334. Min Act: -0.0000

Data Index: 1533770 (The Pile)

Max Activating Token Index: 858