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

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

Neuron 3359 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.8614. Min Act: -0.0001

Data Index: 864432 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.7884. Min Act: -0.0001

Data Index: 654390 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.7648. Min Act: -0.0001

Data Index: 1069614 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.7340. Min Act: -0.0000

Data Index: 406735 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.7399. Min Act: -0.0001

Data Index: 84571 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.7199. Min Act: -0.0001

Data Index: 917529 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.6605. Min Act: -0.0001

Data Index: 155408 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.7230. Min Act: -0.0001

Data Index: 1259848 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.6650. Min Act: -0.0001

Data Index: 392554 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.6395. Min Act: -0.0001

Data Index: 528299 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.6318. Min Act: -0.0001

Data Index: 570410 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.5506. Min Act: -0.0001

Data Index: 334304 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.6308. Min Act: -0.0001

Data Index: 1285767 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.5904. Min Act: -0.0000

Data Index: 113240 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.6390. Min Act: -0.0001

Data Index: 1062495 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.6202. Min Act: -0.0001

Data Index: 505698 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.6193. Min Act: -0.0001

Data Index: 589530 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.5785. Min Act: -0.0001

Data Index: 714285 (C4 (Web Text))

Max Activating Token Index: 846

Text #18

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.5065. Min Act: -0.0001

Data Index: 608408 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.5728. Min Act: -0.0001

Data Index: 301663 (C4 (Web Text))

Max Activating Token Index: 491