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

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

Neuron 3184 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4406. Min Range: -4.4406

Max Act: 4.3151. Min Act: -0.0000

Data Index: 1279188 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 4.4406. Min Range: -4.4406

Max Act: 4.4406. Min Act: -0.0000

Data Index: 497987 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 4.4406. Min Range: -4.4406

Max Act: 3.9141. Min Act: -0.0000

Data Index: 1173959 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 4.4406. Min Range: -4.4406

Max Act: 4.0984. Min Act: -0.0000

Data Index: 853661 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 4.4406. Min Range: -4.4406

Max Act: 4.0197. Min Act: -0.0000

Data Index: 540237 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 4.4406. Min Range: -4.4406

Max Act: 3.5239. Min Act: -0.0000

Data Index: 354569 (C4 (Web Text))

Max Activating Token Index: 384

Text #6

Max Range: 4.4406. Min Range: -4.4406

Max Act: 3.9919. Min Act: -0.0000

Data Index: 971042 (C4 (Web Text))

Max Activating Token Index: 931

Text #7

Max Range: 4.4406. Min Range: -4.4406

Max Act: 3.9376. Min Act: -0.0000

Data Index: 973582 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 4.4406. Min Range: -4.4406

Max Act: 3.8420. Min Act: -0.0000

Data Index: 1220853 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 4.4406. Min Range: -4.4406

Max Act: 3.9728. Min Act: -0.0000

Data Index: 514645 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 4.4406. Min Range: -4.4406

Max Act: 3.7515. Min Act: -0.0000

Data Index: 792629 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 4.4406. Min Range: -4.4406

Max Act: 3.5869. Min Act: -0.0000

Data Index: 338877 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 4.4406. Min Range: -4.4406

Max Act: 3.8173. Min Act: -0.0000

Data Index: 150227 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 4.4406. Min Range: -4.4406

Max Act: 3.3251. Min Act: -0.0000

Data Index: 660916 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 4.4406. Min Range: -4.4406

Max Act: 3.6264. Min Act: -0.0000

Data Index: 1497543 (Python Code)

Max Activating Token Index: 745

Text #15

Max Range: 4.4406. Min Range: -4.4406

Max Act: 3.4745. Min Act: -0.0000

Data Index: 546651 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 4.4406. Min Range: -4.4406

Max Act: 3.6154. Min Act: -0.0000

Data Index: 284565 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 4.4406. Min Range: -4.4406

Max Act: 3.4652. Min Act: -0.0000

Data Index: 50592 (C4 (Web Text))

Max Activating Token Index: 468

Text #18

Max Range: 4.4406. Min Range: -4.4406

Max Act: 3.2959. Min Act: -0.0000

Data Index: 983060 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 4.4406. Min Range: -4.4406

Max Act: 3.7392. Min Act: -0.0000

Data Index: 890418 (C4 (Web Text))

Max Activating Token Index: 216