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

Dataset: The Pile

Neuron 4939 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.2096. Min Act: -0.0000

Data Index: 47177 (The Pile)

Max Activating Token Index: 813

Text #1

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1487. Min Act: -0.0000

Data Index: 1277380 (The Pile)

Max Activating Token Index: 737

Text #2

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1547. Min Act: -0.0000

Data Index: 623241 (The Pile)

Max Activating Token Index: 588

Text #3

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1574. Min Act: -0.0000

Data Index: 1705651 (The Pile)

Max Activating Token Index: 926

Text #4

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1469. Min Act: -0.0000

Data Index: 564169 (The Pile)

Max Activating Token Index: 247

Text #5

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1520. Min Act: -0.0000

Data Index: 1354008 (The Pile)

Max Activating Token Index: 241

Text #6

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1523. Min Act: -0.0000

Data Index: 1917422 (The Pile)

Max Activating Token Index: 265

Text #7

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1452. Min Act: -0.0000

Data Index: 1613290 (The Pile)

Max Activating Token Index: 622

Text #8

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1330. Min Act: -0.0000

Data Index: 112964 (The Pile)

Max Activating Token Index: 529

Text #9

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1348. Min Act: -0.0000

Data Index: 203076 (The Pile)

Max Activating Token Index: 704

Text #10

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1393. Min Act: -0.0000

Data Index: 478323 (The Pile)

Max Activating Token Index: 918

Text #11

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1491. Min Act: -0.0000

Data Index: 1751925 (The Pile)

Max Activating Token Index: 140

Text #12

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1393. Min Act: -0.0000

Data Index: 1427616 (The Pile)

Max Activating Token Index: 439

Text #13

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1091. Min Act: -0.0000

Data Index: 1402268 (The Pile)

Max Activating Token Index: 923

Text #14

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1265. Min Act: -0.0000

Data Index: 347945 (The Pile)

Max Activating Token Index: 76

Text #15

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1257. Min Act: -0.0000

Data Index: 1984343 (The Pile)

Max Activating Token Index: 872

Text #16

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1399. Min Act: -0.0000

Data Index: 662446 (The Pile)

Max Activating Token Index: 914

Text #17

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1319. Min Act: -0.0000

Data Index: 1153652 (The Pile)

Max Activating Token Index: 159

Text #18

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1337. Min Act: -0.0000

Data Index: 648961 (The Pile)

Max Activating Token Index: 334

Text #19

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1463. Min Act: -0.0000

Data Index: 1335372 (The Pile)

Max Activating Token Index: 665