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

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

Neuron 3117 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: 0.9047. Min Range: -0.9047

Max Act: 0.8840. Min Act: -0.0001

Data Index: 1321396 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.9047. Min Act: -0.0001

Data Index: 1129612 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.8513. Min Act: -0.0001

Data Index: 1487091 (Python Code)

Max Activating Token Index: 320

Text #3

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.8917. Min Act: -0.0001

Data Index: 444298 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.8299. Min Act: -0.0001

Data Index: 298422 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.8609. Min Act: -0.0001

Data Index: 970216 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.8413. Min Act: -0.0000

Data Index: 704064 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.7940. Min Act: -0.0001

Data Index: 1312744 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.7543. Min Act: -0.0001

Data Index: 1467433 (Python Code)

Max Activating Token Index: 127

Text #9

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.7807. Min Act: -0.0001

Data Index: 1191320 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.8276. Min Act: -0.0001

Data Index: 1520779 (Python Code)

Max Activating Token Index: 133

Text #11

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.7730. Min Act: -0.0000

Data Index: 963262 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.7880. Min Act: -0.0001

Data Index: 302560 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.7881. Min Act: -0.0001

Data Index: 1158706 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.7311. Min Act: -0.0001

Data Index: 1488412 (Python Code)

Max Activating Token Index: 772

Text #15

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.7737. Min Act: -0.0001

Data Index: 274097 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.7760. Min Act: -0.0001

Data Index: 1640211 (Python Code)

Max Activating Token Index: 531

Text #17

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.7732. Min Act: -0.0000

Data Index: 357909 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.7727. Min Act: -0.0001

Data Index: 48584 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.7549. Min Act: -0.0000

Data Index: 1316717 (C4 (Web Text))

Max Activating Token Index: 40