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

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

Neuron 380 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0483. Min Act: -0.0002

Data Index: 1015223 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0002

Data Index: 524929 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0475. Min Act: -0.0002

Data Index: 796816 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0427. Min Act: -0.0002

Data Index: 934291 (C4 (Web Text))

Max Activating Token Index: 585

Text #4

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0498. Min Act: -0.0002

Data Index: 1154017 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0453. Min Act: -0.0002

Data Index: 769675 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0471. Min Act: -0.0002

Data Index: 553996 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0462. Min Act: -0.0002

Data Index: 376234 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0483. Min Act: -0.0002

Data Index: 81220 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0450. Min Act: -0.0002

Data Index: 880180 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0435. Min Act: -0.0002

Data Index: 868901 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0452. Min Act: -0.0002

Data Index: 189554 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1257743 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0472. Min Act: -0.0002

Data Index: 1053422 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0453. Min Act: -0.0002

Data Index: 1317786 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0394. Min Act: -0.0002

Data Index: 726425 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0403. Min Act: -0.0002

Data Index: 1516977 (Python Code)

Max Activating Token Index: 462

Text #17

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0413. Min Act: -0.0002

Data Index: 856026 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0410. Min Act: -0.0002

Data Index: 1105880 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0420. Min Act: -0.0002

Data Index: 1153274 (C4 (Web Text))

Max Activating Token Index: 655