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

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

Neuron 1363 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.6760. Min Act: -0.0000

Data Index: 551754 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.6954. Min Act: -0.0000

Data Index: 6990 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.6554. Min Act: -0.0000

Data Index: 287242 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.6224. Min Act: -0.0000

Data Index: 148989 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.6319. Min Act: -0.0000

Data Index: 104938 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5490. Min Act: 0.0004

Data Index: 1225301 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5640. Min Act: 0.0001

Data Index: 592617 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5782. Min Act: -0.0000

Data Index: 460522 (C4 (Web Text))

Max Activating Token Index: 422

Text #8

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5437. Min Act: -0.0000

Data Index: 186980 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5676. Min Act: -0.0000

Data Index: 975623 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5565. Min Act: 0.0001

Data Index: 899584 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5562. Min Act: -0.0000

Data Index: 883165 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5302. Min Act: -0.0000

Data Index: 20100 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5478. Min Act: 0.0001

Data Index: 1181999 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5443. Min Act: -0.0000

Data Index: 1158248 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5253. Min Act: 0.0001

Data Index: 597868 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5154. Min Act: 0.0002

Data Index: 1020716 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5278. Min Act: -0.0000

Data Index: 1041337 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5110. Min Act: -0.0000

Data Index: 501294 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.4928. Min Act: 0.0001

Data Index: 1171444 (C4 (Web Text))

Max Activating Token Index: 120