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

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

Neuron 386 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9181. Min Range: -1.9181

Max Act: 1.7397. Min Act: -0.0000

Data Index: 344383 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 1.9181. Min Range: -1.9181

Max Act: 1.7791. Min Act: -0.0000

Data Index: 1301797 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 1.9181. Min Range: -1.9181

Max Act: 1.6702. Min Act: -0.0000

Data Index: 264449 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 1.9181. Min Range: -1.9181

Max Act: 1.9181. Min Act: -0.0000

Data Index: 1138875 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 1.9181. Min Range: -1.9181

Max Act: 1.5747. Min Act: -0.0000

Data Index: 830575 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 1.9181. Min Range: -1.9181

Max Act: 1.4357. Min Act: -0.0000

Data Index: 1180173 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 1.9181. Min Range: -1.9181

Max Act: 1.4346. Min Act: -0.0000

Data Index: 82692 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 1.9181. Min Range: -1.9181

Max Act: 1.4735. Min Act: -0.0000

Data Index: 564892 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 1.9181. Min Range: -1.9181

Max Act: 1.5305. Min Act: -0.0000

Data Index: 41285 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 1.9181. Min Range: -1.9181

Max Act: 1.4378. Min Act: -0.0000

Data Index: 299403 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 1.9181. Min Range: -1.9181

Max Act: 1.5633. Min Act: -0.0000

Data Index: 250374 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 1.9181. Min Range: -1.9181

Max Act: 1.5002. Min Act: -0.0000

Data Index: 679867 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 1.9181. Min Range: -1.9181

Max Act: 1.4073. Min Act: -0.0000

Data Index: 836554 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 1.9181. Min Range: -1.9181

Max Act: 1.4124. Min Act: -0.0000

Data Index: 581251 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 1.9181. Min Range: -1.9181

Max Act: 1.4750. Min Act: -0.0000

Data Index: 980096 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 1.9181. Min Range: -1.9181

Max Act: 1.3939. Min Act: -0.0000

Data Index: 95763 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 1.9181. Min Range: -1.9181

Max Act: 1.3019. Min Act: -0.0000

Data Index: 1069493 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 1.9181. Min Range: -1.9181

Max Act: 1.2242. Min Act: -0.0000

Data Index: 578959 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 1.9181. Min Range: -1.9181

Max Act: 1.2876. Min Act: -0.0000

Data Index: 1124141 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 1.9181. Min Range: -1.9181

Max Act: 1.5214. Min Act: -0.0000

Data Index: 1321760 (C4 (Web Text))

Max Activating Token Index: 743