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

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

Neuron 2706 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.4456. Min Act: -0.0000

Data Index: 1162451 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.4317. Min Act: -0.0001

Data Index: 1243378 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3735. Min Act: -0.0000

Data Index: 903344 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3674. Min Act: -0.0001

Data Index: 342022 (C4 (Web Text))

Max Activating Token Index: 279

Text #4

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3462. Min Act: -0.0000

Data Index: 895078 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3622. Min Act: -0.0001

Data Index: 1282781 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3882. Min Act: -0.0001

Data Index: 632280 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3351. Min Act: -0.0000

Data Index: 909464 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3391. Min Act: -0.0000

Data Index: 977862 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3425. Min Act: -0.0000

Data Index: 642057 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3413. Min Act: -0.0000

Data Index: 388167 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3238. Min Act: -0.0001

Data Index: 1067768 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3325. Min Act: -0.0000

Data Index: 533727 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3063. Min Act: -0.0000

Data Index: 1016261 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3062. Min Act: -0.0001

Data Index: 1220817 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3114. Min Act: -0.0001

Data Index: 1221187 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.2992. Min Act: -0.0000

Data Index: 1147410 (C4 (Web Text))

Max Activating Token Index: 877

Text #17

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3001. Min Act: -0.0000

Data Index: 499055 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.2974. Min Act: -0.0001

Data Index: 473006 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.2868. Min Act: -0.0001

Data Index: 1113273 (C4 (Web Text))

Max Activating Token Index: 732