Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1552 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4902. Min Act: -0.0001

Data Index: 1058583 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4346. Min Act: -0.0001

Data Index: 960276 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4410. Min Act: -0.0001

Data Index: 980915 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4168. Min Act: -0.0001

Data Index: 874389 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3764. Min Act: -0.0001

Data Index: 499375 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3733. Min Act: -0.0001

Data Index: 857388 (C4 (Web Text))

Max Activating Token Index: 449

Text #6

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3585. Min Act: -0.0001

Data Index: 435978 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3489. Min Act: -0.0001

Data Index: 358113 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3585. Min Act: -0.0001

Data Index: 613759 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3694. Min Act: -0.0001

Data Index: 1003605 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3545. Min Act: -0.0001

Data Index: 884510 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3622. Min Act: -0.0001

Data Index: 747013 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3992. Min Act: -0.0001

Data Index: 1253407 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3471. Min Act: -0.0001

Data Index: 1141471 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3713. Min Act: -0.0001

Data Index: 496824 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3706. Min Act: -0.0001

Data Index: 1297175 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3721. Min Act: -0.0001

Data Index: 657891 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3313. Min Act: -0.0001

Data Index: 725569 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3513. Min Act: -0.0001

Data Index: 356521 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3500. Min Act: -0.0001

Data Index: 218429 (C4 (Web Text))

Max Activating Token Index: 401