Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3401 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0434. Min Act: -0.0003

Data Index: 179396 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0442. Min Act: -0.0003

Data Index: 1329973 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0402. Min Act: -0.0003

Data Index: 793029 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0413. Min Act: -0.0003

Data Index: 133325 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0476. Min Act: -0.0003

Data Index: 551 (C4 (Web Text))

Max Activating Token Index: 271

Text #5

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0447. Min Act: -0.0003

Data Index: 1132969 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0409. Min Act: -0.0003

Data Index: 379939 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0425. Min Act: -0.0003

Data Index: 758747 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0416. Min Act: -0.0003

Data Index: 1360561 (Python Code)

Max Activating Token Index: 418

Text #9

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0390. Min Act: -0.0003

Data Index: 1131797 (C4 (Web Text))

Max Activating Token Index: 296

Text #10

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0375. Min Act: -0.0003

Data Index: 90538 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0393. Min Act: -0.0003

Data Index: 472473 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0403. Min Act: -0.0003

Data Index: 279022 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0381. Min Act: -0.0003

Data Index: 528480 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0403. Min Act: -0.0003

Data Index: 1350921 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0408. Min Act: -0.0003

Data Index: 753121 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0404. Min Act: -0.0003

Data Index: 1636155 (Python Code)

Max Activating Token Index: 432

Text #17

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0361. Min Act: -0.0003

Data Index: 584364 (C4 (Web Text))

Max Activating Token Index: 628

Text #18

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0371. Min Act: -0.0003

Data Index: 659100 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0370. Min Act: -0.0003

Data Index: 656103 (C4 (Web Text))

Max Activating Token Index: 580