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

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

Neuron 4276 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7968. Min Range: -1.7968

Max Act: 1.7968. Min Act: -0.0000

Data Index: 262385 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 1.7968. Min Range: -1.7968

Max Act: 1.7949. Min Act: -0.0001

Data Index: 506802 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 1.7968. Min Range: -1.7968

Max Act: 1.3561. Min Act: -0.0000

Data Index: 1051882 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 1.7968. Min Range: -1.7968

Max Act: 1.2285. Min Act: -0.0001

Data Index: 679386 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 1.7968. Min Range: -1.7968

Max Act: 1.2412. Min Act: -0.0001

Data Index: 675493 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 1.7968. Min Range: -1.7968

Max Act: 1.1319. Min Act: -0.0001

Data Index: 783235 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 1.7968. Min Range: -1.7968

Max Act: 1.2022. Min Act: -0.0001

Data Index: 612553 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 1.7968. Min Range: -1.7968

Max Act: 1.1729. Min Act: -0.0001

Data Index: 1109334 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 1.7968. Min Range: -1.7968

Max Act: 1.1228. Min Act: -0.0000

Data Index: 1278317 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 1.7968. Min Range: -1.7968

Max Act: 1.1925. Min Act: -0.0001

Data Index: 403355 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 1.7968. Min Range: -1.7968

Max Act: 1.2411. Min Act: -0.0001

Data Index: 1225369 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 1.7968. Min Range: -1.7968

Max Act: 1.2111. Min Act: -0.0001

Data Index: 1332257 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 1.7968. Min Range: -1.7968

Max Act: 1.1338. Min Act: -0.0000

Data Index: 294230 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 1.7968. Min Range: -1.7968

Max Act: 1.0832. Min Act: -0.0001

Data Index: 890729 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 1.7968. Min Range: -1.7968

Max Act: 1.1047. Min Act: -0.0001

Data Index: 933363 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 1.7968. Min Range: -1.7968

Max Act: 1.1028. Min Act: -0.0001

Data Index: 1272252 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 1.7968. Min Range: -1.7968

Max Act: 1.0317. Min Act: -0.0001

Data Index: 919275 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 1.7968. Min Range: -1.7968

Max Act: 1.0495. Min Act: -0.0000

Data Index: 794819 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 1.7968. Min Range: -1.7968

Max Act: 1.0230. Min Act: -0.0001

Data Index: 991280 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 1.7968. Min Range: -1.7968

Max Act: 0.9497. Min Act: -0.0001

Data Index: 304477 (C4 (Web Text))

Max Activating Token Index: 150