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

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

Neuron 5111 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.4619. Min Act: -0.0000

Data Index: 364252 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.4312. Min Act: -0.0000

Data Index: 578826 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.3496. Min Act: -0.0000

Data Index: 619949 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.3425. Min Act: -0.0000

Data Index: 375527 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.3494. Min Act: -0.0000

Data Index: 1338409 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.3322. Min Act: -0.0000

Data Index: 1183040 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.3188. Min Act: -0.0000

Data Index: 911351 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.3104. Min Act: -0.0000

Data Index: 152417 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.2888. Min Act: -0.0000

Data Index: 637051 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.2824. Min Act: -0.0000

Data Index: 853310 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.2564. Min Act: 0.0000

Data Index: 238018 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.2560. Min Act: -0.0000

Data Index: 67371 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.2631. Min Act: -0.0000

Data Index: 1147143 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.2624. Min Act: -0.0000

Data Index: 257477 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.2605. Min Act: -0.0000

Data Index: 436894 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.2407. Min Act: -0.0000

Data Index: 1299179 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.2448. Min Act: -0.0000

Data Index: 610745 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.2339. Min Act: -0.0000

Data Index: 469942 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.2422. Min Act: -0.0000

Data Index: 810510 (C4 (Web Text))

Max Activating Token Index: 504

Text #19

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.2486. Min Act: -0.0000

Data Index: 898906 (C4 (Web Text))

Max Activating Token Index: 1017