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

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

Neuron 5158 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.3210. Min Act: -0.0000

Data Index: 507243 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.3324. Min Act: -0.0000

Data Index: 1270617 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2815. Min Act: -0.0000

Data Index: 1316669 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2905. Min Act: -0.0000

Data Index: 1133282 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2915. Min Act: -0.0000

Data Index: 1115382 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2865. Min Act: -0.0000

Data Index: 1045537 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2738. Min Act: -0.0000

Data Index: 205107 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2750. Min Act: -0.0000

Data Index: 483461 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2666. Min Act: -0.0000

Data Index: 413850 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2724. Min Act: -0.0000

Data Index: 941957 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2641. Min Act: -0.0000

Data Index: 789445 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2632. Min Act: -0.0000

Data Index: 1151190 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2666. Min Act: -0.0000

Data Index: 150972 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2736. Min Act: -0.0000

Data Index: 401833 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2717. Min Act: -0.0000

Data Index: 134333 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2727. Min Act: -0.0000

Data Index: 577452 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2610. Min Act: -0.0000

Data Index: 1209567 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2615. Min Act: -0.0000

Data Index: 243006 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2778. Min Act: -0.0000

Data Index: 939233 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2589. Min Act: -0.0000

Data Index: 377068 (C4 (Web Text))

Max Activating Token Index: 433