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

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

Neuron 3637 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.4110. Min Act: -0.0001

Data Index: 979086 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3569. Min Act: -0.0001

Data Index: 373870 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3369. Min Act: -0.0001

Data Index: 661108 (C4 (Web Text))

Max Activating Token Index: 421

Text #3

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3324. Min Act: -0.0001

Data Index: 210215 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3240. Min Act: -0.0001

Data Index: 1281951 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3317. Min Act: -0.0001

Data Index: 1354469 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3300. Min Act: -0.0001

Data Index: 585128 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.2842. Min Act: -0.0001

Data Index: 94252 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.2869. Min Act: -0.0001

Data Index: 499373 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.2770. Min Act: -0.0001

Data Index: 1177499 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.2851. Min Act: -0.0001

Data Index: 201242 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.2723. Min Act: -0.0001

Data Index: 194823 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.2742. Min Act: -0.0001

Data Index: 1216838 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.2807. Min Act: -0.0001

Data Index: 1255305 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.2724. Min Act: -0.0001

Data Index: 509814 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.2669. Min Act: -0.0001

Data Index: 1139386 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.2642. Min Act: -0.0001

Data Index: 605106 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.2553. Min Act: -0.0001

Data Index: 1254468 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.2634. Min Act: -0.0001

Data Index: 81186 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.2529. Min Act: -0.0001

Data Index: 415538 (C4 (Web Text))

Max Activating Token Index: 494