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

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

Neuron 1478 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7738. Min Range: -2.7738

Max Act: 2.7738. Min Act: -0.0000

Data Index: 698920 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 2.7738. Min Range: -2.7738

Max Act: 2.3188. Min Act: -0.0000

Data Index: 699204 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 2.7738. Min Range: -2.7738

Max Act: 2.1602. Min Act: -0.0000

Data Index: 617807 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 2.7738. Min Range: -2.7738

Max Act: 2.1851. Min Act: -0.0000

Data Index: 732096 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 2.7738. Min Range: -2.7738

Max Act: 2.1845. Min Act: -0.0000

Data Index: 79513 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 2.7738. Min Range: -2.7738

Max Act: 2.1238. Min Act: -0.0000

Data Index: 122742 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 2.7738. Min Range: -2.7738

Max Act: 2.0017. Min Act: -0.0000

Data Index: 603145 (C4 (Web Text))

Max Activating Token Index: 593

Text #7

Max Range: 2.7738. Min Range: -2.7738

Max Act: 1.9146. Min Act: -0.0000

Data Index: 1079261 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 2.7738. Min Range: -2.7738

Max Act: 1.9163. Min Act: -0.0000

Data Index: 236872 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 2.7738. Min Range: -2.7738

Max Act: 1.8729. Min Act: -0.0000

Data Index: 689129 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 2.7738. Min Range: -2.7738

Max Act: 1.7372. Min Act: -0.0000

Data Index: 392689 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 2.7738. Min Range: -2.7738

Max Act: 1.9224. Min Act: -0.0000

Data Index: 717365 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 2.7738. Min Range: -2.7738

Max Act: 1.5731. Min Act: -0.0000

Data Index: 778305 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 2.7738. Min Range: -2.7738

Max Act: 1.7392. Min Act: -0.0000

Data Index: 366974 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 2.7738. Min Range: -2.7738

Max Act: 1.7385. Min Act: -0.0000

Data Index: 256589 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 2.7738. Min Range: -2.7738

Max Act: 1.7291. Min Act: -0.0000

Data Index: 824788 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 2.7738. Min Range: -2.7738

Max Act: 1.7191. Min Act: -0.0000

Data Index: 34848 (C4 (Web Text))

Max Activating Token Index: 549

Text #17

Max Range: 2.7738. Min Range: -2.7738

Max Act: 1.6215. Min Act: -0.0000

Data Index: 990057 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 2.7738. Min Range: -2.7738

Max Act: 1.6903. Min Act: -0.0000

Data Index: 740052 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 2.7738. Min Range: -2.7738

Max Act: 1.6765. Min Act: -0.0000

Data Index: 873362 (C4 (Web Text))

Max Activating Token Index: 837