Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4862 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1411. Min Act: -0.0000

Data Index: 897070 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1224. Min Act: -0.0000

Data Index: 420742 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1377. Min Act: -0.0000

Data Index: 1578416 (Python Code)

Max Activating Token Index: 740

Text #3

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1334. Min Act: -0.0000

Data Index: 1495268 (Python Code)

Max Activating Token Index: 323

Text #4

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1075. Min Act: -0.0000

Data Index: 1502130 (Python Code)

Max Activating Token Index: 628

Text #5

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1089. Min Act: -0.0000

Data Index: 1644939 (Python Code)

Max Activating Token Index: 552

Text #6

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1054. Min Act: -0.0000

Data Index: 1652908 (Python Code)

Max Activating Token Index: 613

Text #7

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.0954. Min Act: -0.0000

Data Index: 1579459 (Python Code)

Max Activating Token Index: 749

Text #8

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.0858. Min Act: -0.0000

Data Index: 1309056 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.0908. Min Act: -0.0000

Data Index: 1474746 (Python Code)

Max Activating Token Index: 858

Text #10

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.0864. Min Act: -0.0000

Data Index: 1495747 (Python Code)

Max Activating Token Index: 691

Text #11

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.0872. Min Act: -0.0000

Data Index: 1616727 (Python Code)

Max Activating Token Index: 384

Text #12

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.0786. Min Act: -0.0000

Data Index: 1161061 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.0841. Min Act: -0.0000

Data Index: 1531523 (Python Code)

Max Activating Token Index: 198

Text #14

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.0803. Min Act: -0.0000

Data Index: 1592283 (Python Code)

Max Activating Token Index: 592

Text #15

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.0817. Min Act: -0.0000

Data Index: 1173297 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.0849. Min Act: -0.0000

Data Index: 535084 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.0830. Min Act: -0.0000

Data Index: 83763 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.0809. Min Act: -0.0000

Data Index: 1325515 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.0697. Min Act: -0.0000

Data Index: 1381001 (Python Code)

Max Activating Token Index: 719