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

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

Neuron 2481 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.4680. Min Act: -0.0000

Data Index: 1191080 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.4371. Min Act: -0.0000

Data Index: 216486 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.4205. Min Act: -0.0000

Data Index: 609392 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.3876. Min Act: -0.0000

Data Index: 303686 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.4081. Min Act: -0.0000

Data Index: 841752 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.4005. Min Act: -0.0000

Data Index: 232801 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.3814. Min Act: -0.0000

Data Index: 102546 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.3847. Min Act: -0.0000

Data Index: 657637 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.3497. Min Act: -0.0000

Data Index: 1282009 (C4 (Web Text))

Max Activating Token Index: 646

Text #9

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.3454. Min Act: -0.0000

Data Index: 669062 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.3511. Min Act: -0.0000

Data Index: 229538 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.3365. Min Act: -0.0000

Data Index: 385168 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.3271. Min Act: -0.0000

Data Index: 884259 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.3396. Min Act: -0.0000

Data Index: 1156730 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.3222. Min Act: -0.0000

Data Index: 843359 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.3752. Min Act: -0.0000

Data Index: 562786 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.3119. Min Act: -0.0000

Data Index: 254999 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.3433. Min Act: -0.0000

Data Index: 602600 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.3769. Min Act: -0.0000

Data Index: 1186040 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 0.4680. Min Range: -0.4680

Max Act: 0.3351. Min Act: -0.0000

Data Index: 1265105 (C4 (Web Text))

Max Activating Token Index: 669