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

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

Neuron 2854 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: 0.6779. Min Range: -0.6779

Max Act: 0.6779. Min Act: -0.0001

Data Index: 34708 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.6466. Min Act: -0.0000

Data Index: 1269369 (C4 (Web Text))

Max Activating Token Index: 324

Text #2

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.6499. Min Act: -0.0001

Data Index: 1126756 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.6604. Min Act: -0.0001

Data Index: 1537332 (Python Code)

Max Activating Token Index: 40

Text #4

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.6440. Min Act: -0.0001

Data Index: 186228 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.6034. Min Act: -0.0001

Data Index: 1193336 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.6025. Min Act: -0.0001

Data Index: 443249 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5933. Min Act: -0.0000

Data Index: 1202099 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.6254. Min Act: -0.0001

Data Index: 1419325 (Python Code)

Max Activating Token Index: 64

Text #9

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.6223. Min Act: -0.0001

Data Index: 1499730 (Python Code)

Max Activating Token Index: 196

Text #10

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.6481. Min Act: -0.0000

Data Index: 406717 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5888. Min Act: -0.0001

Data Index: 1415218 (Python Code)

Max Activating Token Index: 116

Text #12

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.6172. Min Act: -0.0000

Data Index: 305170 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5793. Min Act: -0.0001

Data Index: 967401 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5782. Min Act: -0.0000

Data Index: 1280901 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5485. Min Act: -0.0000

Data Index: 1217240 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5289. Min Act: -0.0001

Data Index: 284730 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5315. Min Act: -0.0001

Data Index: 502649 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5000. Min Act: -0.0000

Data Index: 453062 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5356. Min Act: -0.0000

Data Index: 506951 (C4 (Web Text))

Max Activating Token Index: 241