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

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

Neuron 2754 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4098. Min Range: -3.4098

Max Act: 3.3584. Min Act: -0.0001

Data Index: 828523 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 3.4098. Min Range: -3.4098

Max Act: 3.4098. Min Act: -0.0001

Data Index: 1240826 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.6123. Min Act: -0.0001

Data Index: 586435 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.8528. Min Act: -0.0001

Data Index: 388687 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.5302. Min Act: -0.0001

Data Index: 316734 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.6442. Min Act: -0.0001

Data Index: 297830 (C4 (Web Text))

Max Activating Token Index: 948

Text #6

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.4748. Min Act: -0.0001

Data Index: 1217460 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.4027. Min Act: -0.0001

Data Index: 163612 (C4 (Web Text))

Max Activating Token Index: 892

Text #8

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.4917. Min Act: -0.0001

Data Index: 358914 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.3511. Min Act: -0.0001

Data Index: 718704 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.5899. Min Act: -0.0001

Data Index: 727979 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.4533. Min Act: -0.0001

Data Index: 699323 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.3481. Min Act: -0.0001

Data Index: 939112 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.5617. Min Act: -0.0001

Data Index: 710148 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.2186. Min Act: -0.0001

Data Index: 455509 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.4041. Min Act: -0.0001

Data Index: 361218 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.2845. Min Act: -0.0001

Data Index: 1011885 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.3269. Min Act: -0.0001

Data Index: 433501 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.2514. Min Act: -0.0001

Data Index: 1242803 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 3.4098. Min Range: -3.4098

Max Act: 1.8431. Min Act: -0.0001

Data Index: 594002 (C4 (Web Text))

Max Activating Token Index: 887