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

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

Neuron 3283 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6478. Min Range: -1.6478

Max Act: 1.6478. Min Act: -0.0001

Data Index: 1572730 (Python Code)

Max Activating Token Index: 640

Text #1

Max Range: 1.6478. Min Range: -1.6478

Max Act: 1.4787. Min Act: -0.0001

Data Index: 1629946 (Python Code)

Max Activating Token Index: 51

Text #2

Max Range: 1.6478. Min Range: -1.6478

Max Act: 1.5258. Min Act: -0.0001

Data Index: 1055929 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 1.6478. Min Range: -1.6478

Max Act: 1.5541. Min Act: -0.0001

Data Index: 1536719 (Python Code)

Max Activating Token Index: 628

Text #4

Max Range: 1.6478. Min Range: -1.6478

Max Act: 1.4559. Min Act: -0.0001

Data Index: 1481468 (Python Code)

Max Activating Token Index: 777

Text #5

Max Range: 1.6478. Min Range: -1.6478

Max Act: 1.4790. Min Act: -0.0000

Data Index: 449 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 1.6478. Min Range: -1.6478

Max Act: 1.4475. Min Act: -0.0001

Data Index: 1613935 (Python Code)

Max Activating Token Index: 604

Text #7

Max Range: 1.6478. Min Range: -1.6478

Max Act: 1.3499. Min Act: -0.0000

Data Index: 1001240 (C4 (Web Text))

Max Activating Token Index: 464

Text #8

Max Range: 1.6478. Min Range: -1.6478

Max Act: 1.3906. Min Act: -0.0001

Data Index: 537859 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 1.6478. Min Range: -1.6478

Max Act: 1.3771. Min Act: -0.0001

Data Index: 1562215 (Python Code)

Max Activating Token Index: 336

Text #10

Max Range: 1.6478. Min Range: -1.6478

Max Act: 1.2409. Min Act: -0.0001

Data Index: 584507 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 1.6478. Min Range: -1.6478

Max Act: 1.3922. Min Act: -0.0001

Data Index: 1536926 (Python Code)

Max Activating Token Index: 567

Text #12

Max Range: 1.6478. Min Range: -1.6478

Max Act: 1.3523. Min Act: -0.0001

Data Index: 1647821 (Python Code)

Max Activating Token Index: 179

Text #13

Max Range: 1.6478. Min Range: -1.6478

Max Act: 1.4237. Min Act: -0.0001

Data Index: 1323612 (C4 (Web Text))

Max Activating Token Index: 316

Text #14

Max Range: 1.6478. Min Range: -1.6478

Max Act: 1.3365. Min Act: -0.0001

Data Index: 1120965 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 1.6478. Min Range: -1.6478

Max Act: 1.3080. Min Act: -0.0000

Data Index: 844717 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 1.6478. Min Range: -1.6478

Max Act: 1.2999. Min Act: -0.0001

Data Index: 1313823 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 1.6478. Min Range: -1.6478

Max Act: 1.3776. Min Act: -0.0000

Data Index: 554708 (C4 (Web Text))

Max Activating Token Index: 958

Text #18

Max Range: 1.6478. Min Range: -1.6478

Max Act: 1.3293. Min Act: -0.0001

Data Index: 1017345 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 1.6478. Min Range: -1.6478

Max Act: 1.2466. Min Act: -0.0001

Data Index: 603265 (C4 (Web Text))

Max Activating Token Index: 880