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

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

Neuron 4670 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8466. Min Range: -2.8466

Max Act: 2.8466. Min Act: -0.0000

Data Index: 705382 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 2.8466. Min Range: -2.8466

Max Act: 2.2617. Min Act: -0.0000

Data Index: 885158 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 2.8466. Min Range: -2.8466

Max Act: 1.9820. Min Act: -0.0000

Data Index: 1004860 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 2.8466. Min Range: -2.8466

Max Act: 2.2237. Min Act: -0.0000

Data Index: 605250 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 2.8466. Min Range: -2.8466

Max Act: 1.7995. Min Act: -0.0000

Data Index: 1064014 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 2.8466. Min Range: -2.8466

Max Act: 1.4120. Min Act: -0.0000

Data Index: 201259 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 2.8466. Min Range: -2.8466

Max Act: 1.3695. Min Act: -0.0000

Data Index: 172519 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 2.8466. Min Range: -2.8466

Max Act: 1.3615. Min Act: -0.0000

Data Index: 1287394 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 2.8466. Min Range: -2.8466

Max Act: 1.3161. Min Act: -0.0000

Data Index: 304027 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 2.8466. Min Range: -2.8466

Max Act: 1.3950. Min Act: -0.0000

Data Index: 564585 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 2.8466. Min Range: -2.8466

Max Act: 1.2809. Min Act: -0.0000

Data Index: 419490 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 2.8466. Min Range: -2.8466

Max Act: 1.2745. Min Act: -0.0000

Data Index: 182542 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 2.8466. Min Range: -2.8466

Max Act: 1.1357. Min Act: -0.0000

Data Index: 309076 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 2.8466. Min Range: -2.8466

Max Act: 1.1639. Min Act: -0.0000

Data Index: 1012913 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 2.8466. Min Range: -2.8466

Max Act: 1.2376. Min Act: -0.0000

Data Index: 105825 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 2.8466. Min Range: -2.8466

Max Act: 1.1113. Min Act: -0.0000

Data Index: 632975 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 2.8466. Min Range: -2.8466

Max Act: 1.1047. Min Act: -0.0000

Data Index: 504285 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 2.8466. Min Range: -2.8466

Max Act: 1.1700. Min Act: -0.0000

Data Index: 611223 (C4 (Web Text))

Max Activating Token Index: 290

Text #18

Max Range: 2.8466. Min Range: -2.8466

Max Act: 0.9897. Min Act: -0.0000

Data Index: 1070226 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 2.8466. Min Range: -2.8466

Max Act: 0.9911. Min Act: -0.0000

Data Index: 151624 (C4 (Web Text))

Max Activating Token Index: 1008