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

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

Neuron 2681 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.5069. Min Act: -0.0000

Data Index: 1306167 (C4 (Web Text))

Max Activating Token Index: 631

Text #1

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.4423. Min Act: -0.0000

Data Index: 316944 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.4787. Min Act: -0.0000

Data Index: 774052 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.4568. Min Act: -0.0000

Data Index: 371824 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.2269. Min Act: -0.0000

Data Index: 366717 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.3049. Min Act: -0.0000

Data Index: 439 (C4 (Web Text))

Max Activating Token Index: 404

Text #6

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.1453. Min Act: -0.0000

Data Index: 896631 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.2173. Min Act: -0.0000

Data Index: 1202061 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.1763. Min Act: -0.0000

Data Index: 682297 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.2029. Min Act: -0.0000

Data Index: 1253170 (C4 (Web Text))

Max Activating Token Index: 1012

Text #10

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.1127. Min Act: -0.0000

Data Index: 1151479 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.0785. Min Act: -0.0000

Data Index: 446440 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.1197. Min Act: -0.0000

Data Index: 673331 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.0963. Min Act: -0.0000

Data Index: 599903 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.1251. Min Act: -0.0000

Data Index: 124831 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.1578. Min Act: -0.0000

Data Index: 128753 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.0822. Min Act: -0.0000

Data Index: 613965 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.0586. Min Act: -0.0000

Data Index: 114935 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.0904. Min Act: -0.0000

Data Index: 260964 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.1555. Min Act: -0.0000

Data Index: 853213 (C4 (Web Text))

Max Activating Token Index: 688