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

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

Neuron 4820 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.7567. Min Act: -0.0000

Data Index: 1476815 (Python Code)

Max Activating Token Index: 115

Text #1

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.5509. Min Act: -0.0000

Data Index: 242180 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.4113. Min Act: -0.0000

Data Index: 1629243 (Python Code)

Max Activating Token Index: 472

Text #3

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.3743. Min Act: -0.0000

Data Index: 687039 (C4 (Web Text))

Max Activating Token Index: 565

Text #4

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.4532. Min Act: -0.0000

Data Index: 539928 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.5404. Min Act: -0.0000

Data Index: 1583866 (Python Code)

Max Activating Token Index: 611

Text #6

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.5351. Min Act: -0.0000

Data Index: 1413610 (Python Code)

Max Activating Token Index: 287

Text #7

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.4690. Min Act: -0.0000

Data Index: 789587 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.3272. Min Act: -0.0000

Data Index: 1455765 (Python Code)

Max Activating Token Index: 916

Text #9

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.2818. Min Act: -0.0000

Data Index: 1076568 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.2289. Min Act: -0.0000

Data Index: 1336185 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.2830. Min Act: -0.0000

Data Index: 74197 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.2901. Min Act: -0.0000

Data Index: 1202407 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.2390. Min Act: -0.0000

Data Index: 115399 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.2613. Min Act: -0.0000

Data Index: 1530310 (Python Code)

Max Activating Token Index: 651

Text #15

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.1834. Min Act: -0.0000

Data Index: 633581 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.2393. Min Act: -0.0000

Data Index: 1563378 (Python Code)

Max Activating Token Index: 146

Text #17

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.2176. Min Act: -0.0000

Data Index: 638301 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.2422. Min Act: -0.0000

Data Index: 587489 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.2639. Min Act: -0.0000

Data Index: 605585 (C4 (Web Text))

Max Activating Token Index: 163