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

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

Neuron 1924 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.4516. Min Act: -0.0000

Data Index: 536717 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3551. Min Act: -0.0000

Data Index: 30628 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3741. Min Act: -0.0001

Data Index: 682551 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3588. Min Act: -0.0000

Data Index: 675502 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3537. Min Act: -0.0001

Data Index: 1314076 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3304. Min Act: -0.0001

Data Index: 993275 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3448. Min Act: -0.0000

Data Index: 784638 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3434. Min Act: -0.0001

Data Index: 533475 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3263. Min Act: -0.0000

Data Index: 287706 (C4 (Web Text))

Max Activating Token Index: 803

Text #9

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3234. Min Act: -0.0001

Data Index: 798265 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3226. Min Act: -0.0000

Data Index: 388772 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3202. Min Act: -0.0001

Data Index: 142261 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3426. Min Act: -0.0000

Data Index: 1323043 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3030. Min Act: -0.0000

Data Index: 208148 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3045. Min Act: -0.0001

Data Index: 1025564 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3014. Min Act: -0.0001

Data Index: 1243665 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3250. Min Act: -0.0000

Data Index: 746352 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.2984. Min Act: -0.0001

Data Index: 284434 (C4 (Web Text))

Max Activating Token Index: 530

Text #18

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3015. Min Act: -0.0000

Data Index: 1036166 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3038. Min Act: -0.0000

Data Index: 570810 (C4 (Web Text))

Max Activating Token Index: 1009