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

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

Neuron 28 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.4870. Min Act: -0.0000

Data Index: 977955 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.4487. Min Act: -0.0000

Data Index: 558917 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3968. Min Act: -0.0000

Data Index: 727106 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3924. Min Act: 0.0001

Data Index: 932272 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3605. Min Act: -0.0000

Data Index: 658460 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3584. Min Act: -0.0000

Data Index: 209208 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3545. Min Act: -0.0000

Data Index: 460141 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3530. Min Act: 0.0001

Data Index: 321132 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3498. Min Act: -0.0001

Data Index: 580226 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3469. Min Act: -0.0000

Data Index: 1218402 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3349. Min Act: -0.0000

Data Index: 320307 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3334. Min Act: -0.0000

Data Index: 110108 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3301. Min Act: -0.0001

Data Index: 28589 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3180. Min Act: 0.0001

Data Index: 997807 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3392. Min Act: -0.0000

Data Index: 721306 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3267. Min Act: -0.0000

Data Index: 627278 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3365. Min Act: -0.0000

Data Index: 597640 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3273. Min Act: -0.0000

Data Index: 108299 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3293. Min Act: -0.0000

Data Index: 393298 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 0.4870. Min Range: -0.4870

Max Act: 0.3126. Min Act: -0.0000

Data Index: 1079268 (C4 (Web Text))

Max Activating Token Index: 568