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

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

Neuron 5630 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.5192. Min Act: -0.0000

Data Index: 703579 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.5000. Min Act: -0.0000

Data Index: 175929 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.5007. Min Act: -0.0000

Data Index: 949928 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.4587. Min Act: -0.0000

Data Index: 295468 (C4 (Web Text))

Max Activating Token Index: 481

Text #4

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.4356. Min Act: -0.0000

Data Index: 1235399 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.4326. Min Act: -0.0000

Data Index: 332921 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.4164. Min Act: -0.0000

Data Index: 285029 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.4294. Min Act: -0.0000

Data Index: 567934 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.4241. Min Act: -0.0000

Data Index: 473615 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.4150. Min Act: -0.0000

Data Index: 105312 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.3838. Min Act: -0.0000

Data Index: 1041478 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.3883. Min Act: -0.0000

Data Index: 385594 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.3883. Min Act: -0.0000

Data Index: 1183595 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.3516. Min Act: -0.0000

Data Index: 742457 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.3685. Min Act: -0.0000

Data Index: 278573 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.3939. Min Act: -0.0000

Data Index: 1201753 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.3746. Min Act: -0.0000

Data Index: 639998 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.3784. Min Act: -0.0000

Data Index: 1016853 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.3759. Min Act: -0.0000

Data Index: 897969 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.3509. Min Act: -0.0000

Data Index: 762596 (C4 (Web Text))

Max Activating Token Index: 74