Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5562 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.6803. Min Act: -0.0000

Data Index: 1590332 (Python Code)

Max Activating Token Index: 722

Text #1

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.6001. Min Act: -0.0000

Data Index: 1433445 (Python Code)

Max Activating Token Index: 909

Text #2

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.4566. Min Act: -0.0000

Data Index: 1009859 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.4464. Min Act: -0.0000

Data Index: 207154 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.4969. Min Act: -0.0000

Data Index: 1357607 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.4434. Min Act: -0.0000

Data Index: 1079305 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.4105. Min Act: -0.0000

Data Index: 546993 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.4665. Min Act: -0.0000

Data Index: 284453 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.4128. Min Act: -0.0000

Data Index: 98340 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.4376. Min Act: -0.0000

Data Index: 1445235 (Python Code)

Max Activating Token Index: 54

Text #10

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.3890. Min Act: -0.0000

Data Index: 822366 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.4458. Min Act: -0.0000

Data Index: 312191 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.3960. Min Act: -0.0000

Data Index: 1157289 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.4086. Min Act: -0.0000

Data Index: 972434 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.4019. Min Act: -0.0000

Data Index: 896962 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.3883. Min Act: -0.0000

Data Index: 960525 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.4015. Min Act: -0.0000

Data Index: 479558 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.3626. Min Act: -0.0000

Data Index: 596985 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.4376. Min Act: -0.0000

Data Index: 992357 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.4035. Min Act: -0.0000

Data Index: 1265269 (C4 (Web Text))

Max Activating Token Index: 977