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

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

Neuron 625 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1940. Min Act: -0.0000

Data Index: 190543 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.2107. Min Act: -0.0000

Data Index: 819052 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1983. Min Act: -0.0000

Data Index: 532195 (C4 (Web Text))

Max Activating Token Index: 517

Text #3

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1833. Min Act: -0.0000

Data Index: 457473 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1767. Min Act: -0.0000

Data Index: 19565 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1767. Min Act: -0.0000

Data Index: 816820 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1899. Min Act: -0.0000

Data Index: 74331 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1564. Min Act: -0.0000

Data Index: 410064 (C4 (Web Text))

Max Activating Token Index: 321

Text #8

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1748. Min Act: -0.0000

Data Index: 454577 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1544. Min Act: -0.0000

Data Index: 771297 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1887. Min Act: -0.0000

Data Index: 288411 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1638. Min Act: -0.0000

Data Index: 759344 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1406. Min Act: -0.0000

Data Index: 971413 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1698. Min Act: -0.0000

Data Index: 423667 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1507. Min Act: -0.0000

Data Index: 749806 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1555. Min Act: -0.0000

Data Index: 621719 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1531. Min Act: -0.0000

Data Index: 245769 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1567. Min Act: -0.0000

Data Index: 764173 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1579. Min Act: -0.0000

Data Index: 292961 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1506. Min Act: -0.0000

Data Index: 131573 (C4 (Web Text))

Max Activating Token Index: 501