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

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

Neuron 1333 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: 0.2881. Min Range: -0.2881

Max Act: 0.2324. Min Act: -0.0000

Data Index: 355288 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2861. Min Act: -0.0001

Data Index: 822422 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2856. Min Act: -0.0001

Data Index: 79996 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2821. Min Act: -0.0000

Data Index: 1190150 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2881. Min Act: -0.0001

Data Index: 587559 (C4 (Web Text))

Max Activating Token Index: 933

Text #5

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2776. Min Act: -0.0001

Data Index: 203475 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2652. Min Act: -0.0000

Data Index: 1173593 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2695. Min Act: -0.0000

Data Index: 287889 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2610. Min Act: -0.0000

Data Index: 809471 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2602. Min Act: -0.0000

Data Index: 1338114 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2547. Min Act: -0.0001

Data Index: 659510 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2592. Min Act: -0.0000

Data Index: 526448 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2460. Min Act: -0.0000

Data Index: 508392 (C4 (Web Text))

Max Activating Token Index: 873

Text #13

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2437. Min Act: -0.0000

Data Index: 874100 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2427. Min Act: -0.0001

Data Index: 72651 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2323. Min Act: 0.0000

Data Index: 43233 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2478. Min Act: -0.0000

Data Index: 1140006 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2289. Min Act: -0.0001

Data Index: 322812 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2420. Min Act: -0.0000

Data Index: 865877 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 0.2881. Min Range: -0.2881

Max Act: 0.2343. Min Act: -0.0001

Data Index: 316459 (C4 (Web Text))

Max Activating Token Index: 299