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

Dataset: The Pile

Neuron 1082 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.8012. Min Act: -0.0000

Data Index: 1426478 (The Pile)

Max Activating Token Index: 881

Text #1

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.7345. Min Act: -0.0000

Data Index: 1471771 (The Pile)

Max Activating Token Index: 673

Text #2

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.7893. Min Act: -0.0000

Data Index: 242442 (The Pile)

Max Activating Token Index: 472

Text #3

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.7871. Min Act: -0.0000

Data Index: 191320 (The Pile)

Max Activating Token Index: 615

Text #4

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.7332. Min Act: -0.0000

Data Index: 898767 (The Pile)

Max Activating Token Index: 335

Text #5

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.7313. Min Act: -0.0000

Data Index: 1717584 (The Pile)

Max Activating Token Index: 966

Text #6

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6537. Min Act: -0.0000

Data Index: 823053 (The Pile)

Max Activating Token Index: 941

Text #7

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6675. Min Act: -0.0000

Data Index: 1709099 (The Pile)

Max Activating Token Index: 136

Text #8

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6520. Min Act: -0.0000

Data Index: 1096111 (The Pile)

Max Activating Token Index: 530

Text #9

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6472. Min Act: -0.0000

Data Index: 1320973 (The Pile)

Max Activating Token Index: 759

Text #10

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6432. Min Act: -0.0000

Data Index: 1220715 (The Pile)

Max Activating Token Index: 773

Text #11

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6570. Min Act: -0.0000

Data Index: 1467513 (The Pile)

Max Activating Token Index: 251

Text #12

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6300. Min Act: 0.0000

Data Index: 1364092 (The Pile)

Max Activating Token Index: 645

Text #13

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6894. Min Act: -0.0000

Data Index: 323344 (The Pile)

Max Activating Token Index: 1006

Text #14

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.7050. Min Act: -0.0000

Data Index: 1998231 (The Pile)

Max Activating Token Index: 882

Text #15

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6107. Min Act: -0.0000

Data Index: 1789901 (The Pile)

Max Activating Token Index: 723

Text #16

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6096. Min Act: -0.0000

Data Index: 1956165 (The Pile)

Max Activating Token Index: 352

Text #17

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6285. Min Act: -0.0000

Data Index: 1442673 (The Pile)

Max Activating Token Index: 26

Text #18

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6253. Min Act: 0.0000

Data Index: 115780 (The Pile)

Max Activating Token Index: 663

Text #19

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.5706. Min Act: -0.0000

Data Index: 156206 (The Pile)

Max Activating Token Index: 448