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

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

Neuron 746 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: 0.3585. Min Range: -0.3585

Max Act: 0.3539. Min Act: -0.0000

Data Index: 354374 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3409. Min Act: -0.0000

Data Index: 638848 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3453. Min Act: -0.0000

Data Index: 57812 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3358. Min Act: -0.0001

Data Index: 1218963 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3279. Min Act: -0.0000

Data Index: 82427 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3164. Min Act: -0.0001

Data Index: 706875 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3267. Min Act: -0.0001

Data Index: 869643 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3585. Min Act: -0.0001

Data Index: 250200 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3338. Min Act: -0.0001

Data Index: 952142 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3215. Min Act: -0.0001

Data Index: 901181 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3421. Min Act: -0.0000

Data Index: 160075 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3203. Min Act: -0.0000

Data Index: 944184 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3294. Min Act: -0.0001

Data Index: 739584 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.2982. Min Act: -0.0000

Data Index: 524796 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3242. Min Act: -0.0000

Data Index: 1029905 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3043. Min Act: -0.0001

Data Index: 260693 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3307. Min Act: -0.0000

Data Index: 24277 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3026. Min Act: -0.0001

Data Index: 217642 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3170. Min Act: -0.0001

Data Index: 1222757 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3272. Min Act: -0.0000

Data Index: 54092 (C4 (Web Text))

Max Activating Token Index: 428