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

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

Neuron 605 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: 4.8259. Min Range: -4.8259

Max Act: 4.8259. Min Act: -0.0000

Data Index: 194040 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 4.8259. Min Range: -4.8259

Max Act: 4.7653. Min Act: -0.0000

Data Index: 1267783 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 4.8259. Min Range: -4.8259

Max Act: 3.6906. Min Act: -0.0000

Data Index: 656906 (C4 (Web Text))

Max Activating Token Index: 1018

Text #3

Max Range: 4.8259. Min Range: -4.8259

Max Act: 3.8914. Min Act: -0.0000

Data Index: 1243611 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 4.8259. Min Range: -4.8259

Max Act: 3.2095. Min Act: -0.0000

Data Index: 1174631 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 4.8259. Min Range: -4.8259

Max Act: 3.1850. Min Act: -0.0000

Data Index: 829189 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 4.8259. Min Range: -4.8259

Max Act: 3.3133. Min Act: -0.0000

Data Index: 1336374 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 4.8259. Min Range: -4.8259

Max Act: 3.0823. Min Act: -0.0000

Data Index: 1160665 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 4.8259. Min Range: -4.8259

Max Act: 3.1993. Min Act: -0.0000

Data Index: 1010539 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 4.8259. Min Range: -4.8259

Max Act: 3.3650. Min Act: -0.0000

Data Index: 645466 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 4.8259. Min Range: -4.8259

Max Act: 3.2036. Min Act: -0.0000

Data Index: 746494 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 4.8259. Min Range: -4.8259

Max Act: 3.1920. Min Act: -0.0000

Data Index: 807500 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 4.8259. Min Range: -4.8259

Max Act: 3.1399. Min Act: -0.0000

Data Index: 881413 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 4.8259. Min Range: -4.8259

Max Act: 3.1265. Min Act: -0.0000

Data Index: 1116474 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 4.8259. Min Range: -4.8259

Max Act: 3.3405. Min Act: -0.0000

Data Index: 1006796 (C4 (Web Text))

Max Activating Token Index: 737

Text #15

Max Range: 4.8259. Min Range: -4.8259

Max Act: 3.0366. Min Act: -0.0000

Data Index: 1441458 (Python Code)

Max Activating Token Index: 91

Text #16

Max Range: 4.8259. Min Range: -4.8259

Max Act: 3.1535. Min Act: -0.0000

Data Index: 1042062 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 4.8259. Min Range: -4.8259

Max Act: 2.9428. Min Act: -0.0000

Data Index: 1053592 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 4.8259. Min Range: -4.8259

Max Act: 2.9172. Min Act: -0.0000

Data Index: 465536 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 4.8259. Min Range: -4.8259

Max Act: 3.1555. Min Act: -0.0000

Data Index: 190585 (C4 (Web Text))

Max Activating Token Index: 254