Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2693 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.4902. Min Act: -0.0001

Data Index: 346829 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.4402. Min Act: -0.0002

Data Index: 1042532 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.3794. Min Act: -0.0001

Data Index: 152448 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.3593. Min Act: -0.0001

Data Index: 219523 (C4 (Web Text))

Max Activating Token Index: 607

Text #4

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.3147. Min Act: -0.0002

Data Index: 1050485 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.3138. Min Act: -0.0002

Data Index: 1082501 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.3286. Min Act: -0.0002

Data Index: 1079337 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.2822. Min Act: -0.0001

Data Index: 441358 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.3004. Min Act: -0.0002

Data Index: 1077724 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.2838. Min Act: -0.0001

Data Index: 630693 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.2635. Min Act: -0.0001

Data Index: 625355 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.3583. Min Act: -0.0002

Data Index: 955779 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.2887. Min Act: -0.0002

Data Index: 29042 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.1429. Min Act: -0.0002

Data Index: 105813 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.1623. Min Act: -0.0001

Data Index: 841992 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.2267. Min Act: -0.0002

Data Index: 99382 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.2077. Min Act: -0.0002

Data Index: 655298 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.1646. Min Act: -0.0002

Data Index: 158730 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.1950. Min Act: -0.0002

Data Index: 284938 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 1.4902. Min Range: -1.4902

Max Act: 1.2318. Min Act: -0.0001

Data Index: 267672 (C4 (Web Text))

Max Activating Token Index: 589