Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4595 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.9839. Min Range: -5.9839

Max Act: 5.9839. Min Act: -0.0001

Data Index: 839420 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 5.9839. Min Range: -5.9839

Max Act: 4.1659. Min Act: -0.0001

Data Index: 647034 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 5.9839. Min Range: -5.9839

Max Act: 4.4695. Min Act: -0.0001

Data Index: 1022601 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 5.9839. Min Range: -5.9839

Max Act: 2.6037. Min Act: -0.0001

Data Index: 774408 (C4 (Web Text))

Max Activating Token Index: 475

Text #4

Max Range: 5.9839. Min Range: -5.9839

Max Act: 2.3702. Min Act: -0.0001

Data Index: 972507 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 5.9839. Min Range: -5.9839

Max Act: 2.3095. Min Act: -0.0001

Data Index: 1172019 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 5.9839. Min Range: -5.9839

Max Act: 2.1288. Min Act: -0.0001

Data Index: 472261 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 5.9839. Min Range: -5.9839

Max Act: 2.3315. Min Act: -0.0001

Data Index: 1353837 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 5.9839. Min Range: -5.9839

Max Act: 2.1994. Min Act: -0.0001

Data Index: 65064 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 5.9839. Min Range: -5.9839

Max Act: 2.0397. Min Act: -0.0001

Data Index: 668392 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 5.9839. Min Range: -5.9839

Max Act: 2.0585. Min Act: -0.0001

Data Index: 1127776 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 5.9839. Min Range: -5.9839

Max Act: 2.0083. Min Act: -0.0001

Data Index: 209249 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 5.9839. Min Range: -5.9839

Max Act: 1.6336. Min Act: -0.0001

Data Index: 378939 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 5.9839. Min Range: -5.9839

Max Act: 1.6545. Min Act: -0.0001

Data Index: 790425 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 5.9839. Min Range: -5.9839

Max Act: 1.3974. Min Act: -0.0001

Data Index: 308642 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 5.9839. Min Range: -5.9839

Max Act: 2.1041. Min Act: -0.0001

Data Index: 391814 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 5.9839. Min Range: -5.9839

Max Act: 1.6642. Min Act: -0.0001

Data Index: 242719 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 5.9839. Min Range: -5.9839

Max Act: 1.7842. Min Act: -0.0001

Data Index: 242015 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 5.9839. Min Range: -5.9839

Max Act: 1.6060. Min Act: -0.0001

Data Index: 195005 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 5.9839. Min Range: -5.9839

Max Act: 1.6718. Min Act: -0.0001

Data Index: 1336730 (C4 (Web Text))

Max Activating Token Index: 429