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

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

Neuron 3872 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9071. Min Range: -4.9071

Max Act: 4.8855. Min Act: -0.0000

Data Index: 324460 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 4.9071. Min Range: -4.9071

Max Act: 4.9071. Min Act: -0.0000

Data Index: 740314 (C4 (Web Text))

Max Activating Token Index: 487

Text #2

Max Range: 4.9071. Min Range: -4.9071

Max Act: 4.6907. Min Act: -0.0000

Data Index: 397893 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 4.9071. Min Range: -4.9071

Max Act: 4.6489. Min Act: -0.0000

Data Index: 209486 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 4.9071. Min Range: -4.9071

Max Act: 4.3401. Min Act: -0.0000

Data Index: 308519 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 4.9071. Min Range: -4.9071

Max Act: 4.8790. Min Act: -0.0000

Data Index: 76748 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 4.9071. Min Range: -4.9071

Max Act: 4.4155. Min Act: -0.0000

Data Index: 605636 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 4.9071. Min Range: -4.9071

Max Act: 4.3804. Min Act: -0.0000

Data Index: 509120 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 4.9071. Min Range: -4.9071

Max Act: 4.5524. Min Act: -0.0000

Data Index: 76417 (C4 (Web Text))

Max Activating Token Index: 445

Text #9

Max Range: 4.9071. Min Range: -4.9071

Max Act: 4.5337. Min Act: -0.0000

Data Index: 1193347 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 4.9071. Min Range: -4.9071

Max Act: 4.5321. Min Act: -0.0000

Data Index: 132347 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 4.9071. Min Range: -4.9071

Max Act: 4.1815. Min Act: -0.0000

Data Index: 1069152 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 4.9071. Min Range: -4.9071

Max Act: 4.5238. Min Act: -0.0000

Data Index: 304176 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 4.9071. Min Range: -4.9071

Max Act: 4.3376. Min Act: -0.0000

Data Index: 666339 (C4 (Web Text))

Max Activating Token Index: 539

Text #14

Max Range: 4.9071. Min Range: -4.9071

Max Act: 4.4972. Min Act: -0.0000

Data Index: 1270997 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 4.9071. Min Range: -4.9071

Max Act: 4.3844. Min Act: -0.0000

Data Index: 488352 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 4.9071. Min Range: -4.9071

Max Act: 4.3585. Min Act: -0.0000

Data Index: 78485 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 4.9071. Min Range: -4.9071

Max Act: 4.3589. Min Act: -0.0000

Data Index: 522537 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 4.9071. Min Range: -4.9071

Max Act: 4.3520. Min Act: -0.0000

Data Index: 451408 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 4.9071. Min Range: -4.9071

Max Act: 4.3472. Min Act: -0.0000

Data Index: 174607 (C4 (Web Text))

Max Activating Token Index: 750