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

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

Neuron 2112 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.5399. Min Act: -0.0001

Data Index: 1307559 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.4875. Min Act: -0.0001

Data Index: 1232204 (C4 (Web Text))

Max Activating Token Index: 682

Text #2

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.4800. Min Act: -0.0001

Data Index: 286285 (C4 (Web Text))

Max Activating Token Index: 665

Text #3

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.4522. Min Act: -0.0001

Data Index: 985989 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.4373. Min Act: -0.0001

Data Index: 253006 (C4 (Web Text))

Max Activating Token Index: 673

Text #5

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.4262. Min Act: -0.0001

Data Index: 389985 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.4924. Min Act: -0.0001

Data Index: 26933 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.4619. Min Act: -0.0001

Data Index: 368742 (C4 (Web Text))

Max Activating Token Index: 755

Text #8

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.4728. Min Act: -0.0001

Data Index: 948387 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.4523. Min Act: -0.0001

Data Index: 637690 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.4005. Min Act: -0.0001

Data Index: 1318578 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.4600. Min Act: -0.0001

Data Index: 316710 (C4 (Web Text))

Max Activating Token Index: 343

Text #12

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.4854. Min Act: -0.0001

Data Index: 1083245 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.4232. Min Act: -0.0001

Data Index: 173625 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.4445. Min Act: -0.0001

Data Index: 1278821 (C4 (Web Text))

Max Activating Token Index: 444

Text #15

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.4525. Min Act: -0.0001

Data Index: 809624 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.4258. Min Act: -0.0001

Data Index: 970540 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.4483. Min Act: -0.0001

Data Index: 1198236 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.3880. Min Act: -0.0001

Data Index: 810621 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.3972. Min Act: -0.0001

Data Index: 569876 (C4 (Web Text))

Max Activating Token Index: 401