Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1184 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.5535. Min Act: -0.0003

Data Index: 1267679 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4960. Min Act: -0.0003

Data Index: 1153075 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4715. Min Act: -0.0003

Data Index: 1092579 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4826. Min Act: -0.0003

Data Index: 830485 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4793. Min Act: -0.0003

Data Index: 1050003 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4604. Min Act: -0.0003

Data Index: 302861 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4748. Min Act: -0.0003

Data Index: 106090 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4778. Min Act: -0.0003

Data Index: 617557 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4705. Min Act: -0.0003

Data Index: 1091061 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4447. Min Act: -0.0003

Data Index: 259861 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4863. Min Act: -0.0003

Data Index: 1226174 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4735. Min Act: -0.0003

Data Index: 296861 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4450. Min Act: -0.0003

Data Index: 266866 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4404. Min Act: -0.0003

Data Index: 311328 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4551. Min Act: -0.0003

Data Index: 195745 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4290. Min Act: -0.0003

Data Index: 556337 (C4 (Web Text))

Max Activating Token Index: 339

Text #16

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4442. Min Act: -0.0003

Data Index: 243704 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4531. Min Act: -0.0003

Data Index: 280300 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4526. Min Act: -0.0003

Data Index: 912665 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4712. Min Act: -0.0003

Data Index: 107587 (C4 (Web Text))

Max Activating Token Index: 221