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

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

Neuron 1927 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: 0.7339. Min Range: -0.7339

Max Act: 0.7339. Min Act: -0.0000

Data Index: 507931 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.5660. Min Act: -0.0000

Data Index: 245747 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.4684. Min Act: 0.0002

Data Index: 962105 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.4306. Min Act: 0.0001

Data Index: 344388 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.4122. Min Act: -0.0001

Data Index: 708008 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.3997. Min Act: 0.0002

Data Index: 174773 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.3773. Min Act: -0.0000

Data Index: 899165 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.3904. Min Act: -0.0000

Data Index: 123101 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.3695. Min Act: -0.0000

Data Index: 420607 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.3591. Min Act: -0.0000

Data Index: 287098 (C4 (Web Text))

Max Activating Token Index: 434

Text #10

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.3588. Min Act: -0.0001

Data Index: 1356334 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.3567. Min Act: 0.0001

Data Index: 702227 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.3635. Min Act: -0.0000

Data Index: 805404 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.3515. Min Act: -0.0000

Data Index: 741463 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.3347. Min Act: -0.0000

Data Index: 684891 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.3572. Min Act: -0.0000

Data Index: 833471 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.3349. Min Act: -0.0000

Data Index: 934545 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.3140. Min Act: 0.0003

Data Index: 1033403 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.3325. Min Act: -0.0000

Data Index: 494566 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.3433. Min Act: 0.0000

Data Index: 1188977 (C4 (Web Text))

Max Activating Token Index: 489