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

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

Neuron 3529 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: 0.4254. Min Range: -0.4254

Max Act: 0.4254. Min Act: -0.0001

Data Index: 1067253 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3850. Min Act: -0.0001

Data Index: 1154044 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.4014. Min Act: -0.0002

Data Index: 930368 (C4 (Web Text))

Max Activating Token Index: 903

Text #3

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3910. Min Act: -0.0002

Data Index: 712047 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3624. Min Act: -0.0002

Data Index: 1342888 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3841. Min Act: -0.0001

Data Index: 687902 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3649. Min Act: -0.0002

Data Index: 571602 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3573. Min Act: -0.0001

Data Index: 841680 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3235. Min Act: -0.0001

Data Index: 877262 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3364. Min Act: -0.0002

Data Index: 719229 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3121. Min Act: -0.0002

Data Index: 1261999 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3286. Min Act: -0.0002

Data Index: 370017 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3158. Min Act: -0.0002

Data Index: 874218 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.2951. Min Act: -0.0002

Data Index: 482197 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.2949. Min Act: -0.0002

Data Index: 798764 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.2945. Min Act: -0.0002

Data Index: 539528 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3074. Min Act: -0.0001

Data Index: 449770 (C4 (Web Text))

Max Activating Token Index: 549

Text #17

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.2939. Min Act: -0.0001

Data Index: 888074 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3036. Min Act: -0.0002

Data Index: 1197921 (C4 (Web Text))

Max Activating Token Index: 657

Text #19

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3133. Min Act: -0.0001

Data Index: 725438 (C4 (Web Text))

Max Activating Token Index: 238