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

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

Neuron 3407 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.5066. Min Act: -0.0000

Data Index: 515728 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.5407. Min Act: -0.0000

Data Index: 396905 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.5334. Min Act: -0.0000

Data Index: 471039 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.5381. Min Act: -0.0000

Data Index: 901484 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.5468. Min Act: -0.0000

Data Index: 16627 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.5350. Min Act: -0.0000

Data Index: 1297653 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.5157. Min Act: -0.0000

Data Index: 936521 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.5310. Min Act: -0.0000

Data Index: 1088039 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.5260. Min Act: -0.0000

Data Index: 56654 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.5298. Min Act: -0.0000

Data Index: 716765 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.5181. Min Act: -0.0000

Data Index: 1110307 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.4973. Min Act: -0.0000

Data Index: 571476 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.4947. Min Act: -0.0000

Data Index: 583410 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.4907. Min Act: -0.0000

Data Index: 218692 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.4886. Min Act: -0.0000

Data Index: 1125488 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.5070. Min Act: -0.0000

Data Index: 1351988 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.5024. Min Act: -0.0000

Data Index: 452766 (C4 (Web Text))

Max Activating Token Index: 635

Text #17

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.4654. Min Act: -0.0000

Data Index: 969632 (C4 (Web Text))

Max Activating Token Index: 223

Text #18

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.5004. Min Act: -0.0000

Data Index: 299719 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.4830. Min Act: -0.0000

Data Index: 852804 (C4 (Web Text))

Max Activating Token Index: 618