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

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

Neuron 5288 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7105. Min Range: -4.7105

Max Act: 4.7105. Min Act: -0.0000

Data Index: 1223130 (C4 (Web Text))

Max Activating Token Index: 650

Text #1

Max Range: 4.7105. Min Range: -4.7105

Max Act: 4.5700. Min Act: -0.0000

Data Index: 376871 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 4.7105. Min Range: -4.7105

Max Act: 4.1980. Min Act: -0.0000

Data Index: 454273 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 4.7105. Min Range: -4.7105

Max Act: 3.9309. Min Act: -0.0000

Data Index: 963954 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 4.7105. Min Range: -4.7105

Max Act: 3.8738. Min Act: -0.0000

Data Index: 720139 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 4.7105. Min Range: -4.7105

Max Act: 3.4806. Min Act: -0.0000

Data Index: 978632 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 4.7105. Min Range: -4.7105

Max Act: 3.4565. Min Act: -0.0000

Data Index: 1117643 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 4.7105. Min Range: -4.7105

Max Act: 3.5128. Min Act: -0.0000

Data Index: 1038266 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 4.7105. Min Range: -4.7105

Max Act: 3.6207. Min Act: -0.0000

Data Index: 65428 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 4.7105. Min Range: -4.7105

Max Act: 3.4212. Min Act: -0.0000

Data Index: 1206080 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 4.7105. Min Range: -4.7105

Max Act: 3.2345. Min Act: -0.0000

Data Index: 317232 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 4.7105. Min Range: -4.7105

Max Act: 3.2493. Min Act: -0.0000

Data Index: 212459 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 4.7105. Min Range: -4.7105

Max Act: 3.3634. Min Act: -0.0000

Data Index: 490683 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 4.7105. Min Range: -4.7105

Max Act: 3.2058. Min Act: -0.0000

Data Index: 457760 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 4.7105. Min Range: -4.7105

Max Act: 3.1040. Min Act: -0.0000

Data Index: 861001 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 4.7105. Min Range: -4.7105

Max Act: 3.3585. Min Act: -0.0000

Data Index: 1167599 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 4.7105. Min Range: -4.7105

Max Act: 3.1069. Min Act: -0.0000

Data Index: 1063525 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 4.7105. Min Range: -4.7105

Max Act: 3.0302. Min Act: -0.0000

Data Index: 209783 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 4.7105. Min Range: -4.7105

Max Act: 2.8218. Min Act: -0.0000

Data Index: 712618 (C4 (Web Text))

Max Activating Token Index: 871

Text #19

Max Range: 4.7105. Min Range: -4.7105

Max Act: 2.7740. Min Act: -0.0000

Data Index: 899766 (C4 (Web Text))

Max Activating Token Index: 269