Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 768 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0515. Min Range: -1.0515

Max Act: 1.0515. Min Act: -0.0001

Data Index: 312834 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 1.0515. Min Range: -1.0515

Max Act: 1.0402. Min Act: -0.0000

Data Index: 594916 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 1.0515. Min Range: -1.0515

Max Act: 0.9652. Min Act: -0.0001

Data Index: 1333186 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 1.0515. Min Range: -1.0515

Max Act: 0.9888. Min Act: -0.0001

Data Index: 355808 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 1.0515. Min Range: -1.0515

Max Act: 0.9855. Min Act: -0.0000

Data Index: 532464 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 1.0515. Min Range: -1.0515

Max Act: 0.9041. Min Act: -0.0000

Data Index: 474057 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 1.0515. Min Range: -1.0515

Max Act: 0.9279. Min Act: -0.0000

Data Index: 983592 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 1.0515. Min Range: -1.0515

Max Act: 0.8884. Min Act: -0.0000

Data Index: 440659 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 1.0515. Min Range: -1.0515

Max Act: 0.8629. Min Act: -0.0000

Data Index: 78176 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 1.0515. Min Range: -1.0515

Max Act: 0.8871. Min Act: -0.0000

Data Index: 872922 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 1.0515. Min Range: -1.0515

Max Act: 0.8052. Min Act: -0.0001

Data Index: 696095 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 1.0515. Min Range: -1.0515

Max Act: 0.8823. Min Act: -0.0000

Data Index: 312667 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 1.0515. Min Range: -1.0515

Max Act: 0.8705. Min Act: -0.0001

Data Index: 275414 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 1.0515. Min Range: -1.0515

Max Act: 0.8397. Min Act: -0.0000

Data Index: 583133 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 1.0515. Min Range: -1.0515

Max Act: 0.8126. Min Act: -0.0000

Data Index: 1194389 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 1.0515. Min Range: -1.0515

Max Act: 0.8370. Min Act: -0.0000

Data Index: 855289 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 1.0515. Min Range: -1.0515

Max Act: 0.7959. Min Act: -0.0001

Data Index: 1022970 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 1.0515. Min Range: -1.0515

Max Act: 0.8246. Min Act: -0.0000

Data Index: 1118178 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 1.0515. Min Range: -1.0515

Max Act: 0.7895. Min Act: -0.0000

Data Index: 1103176 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 1.0515. Min Range: -1.0515

Max Act: 0.8383. Min Act: -0.0000

Data Index: 85275 (C4 (Web Text))

Max Activating Token Index: 437