Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 299 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0944. Min Range: -2.0944

Max Act: 2.0944. Min Act: -0.0000

Data Index: 1474277 (Python Code)

Max Activating Token Index: 918

Text #1

Max Range: 2.0944. Min Range: -2.0944

Max Act: 1.9553. Min Act: -0.0001

Data Index: 745980 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 2.0944. Min Range: -2.0944

Max Act: 1.5987. Min Act: -0.0000

Data Index: 636848 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 2.0944. Min Range: -2.0944

Max Act: 1.6323. Min Act: -0.0000

Data Index: 796799 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 2.0944. Min Range: -2.0944

Max Act: 1.6460. Min Act: -0.0001

Data Index: 1242774 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 2.0944. Min Range: -2.0944

Max Act: 1.5390. Min Act: -0.0000

Data Index: 475102 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 2.0944. Min Range: -2.0944

Max Act: 1.5568. Min Act: -0.0000

Data Index: 137228 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 2.0944. Min Range: -2.0944

Max Act: 1.5468. Min Act: -0.0001

Data Index: 1165711 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 2.0944. Min Range: -2.0944

Max Act: 1.4703. Min Act: -0.0001

Data Index: 52238 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 2.0944. Min Range: -2.0944

Max Act: 1.4511. Min Act: -0.0000

Data Index: 1288725 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 2.0944. Min Range: -2.0944

Max Act: 1.4067. Min Act: -0.0000

Data Index: 465781 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 2.0944. Min Range: -2.0944

Max Act: 1.3587. Min Act: -0.0000

Data Index: 1171651 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 2.0944. Min Range: -2.0944

Max Act: 1.4342. Min Act: -0.0000

Data Index: 1151464 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 2.0944. Min Range: -2.0944

Max Act: 1.4538. Min Act: -0.0000

Data Index: 1477917 (Python Code)

Max Activating Token Index: 520

Text #14

Max Range: 2.0944. Min Range: -2.0944

Max Act: 1.4184. Min Act: -0.0000

Data Index: 674275 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 2.0944. Min Range: -2.0944

Max Act: 1.3341. Min Act: -0.0000

Data Index: 1525208 (Python Code)

Max Activating Token Index: 228

Text #16

Max Range: 2.0944. Min Range: -2.0944

Max Act: 1.4253. Min Act: -0.0000

Data Index: 369231 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 2.0944. Min Range: -2.0944

Max Act: 1.3468. Min Act: -0.0000

Data Index: 1642141 (Python Code)

Max Activating Token Index: 245

Text #18

Max Range: 2.0944. Min Range: -2.0944

Max Act: 1.2524. Min Act: -0.0000

Data Index: 850423 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 2.0944. Min Range: -2.0944

Max Act: 1.2800. Min Act: -0.0000

Data Index: 464574 (C4 (Web Text))

Max Activating Token Index: 334