Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1086 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0421. Min Act: -0.0003

Data Index: 379523 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0405. Min Act: -0.0002

Data Index: 1648351 (Python Code)

Max Activating Token Index: 805

Text #2

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0412. Min Act: -0.0003

Data Index: 1294293 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0381. Min Act: -0.0004

Data Index: 549041 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0389. Min Act: -0.0003

Data Index: 792157 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0384. Min Act: -0.0003

Data Index: 555440 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0389. Min Act: -0.0003

Data Index: 1533887 (Python Code)

Max Activating Token Index: 954

Text #7

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0387. Min Act: -0.0002

Data Index: 1582702 (Python Code)

Max Activating Token Index: 997

Text #8

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0365. Min Act: -0.0003

Data Index: 969870 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0375. Min Act: -0.0004

Data Index: 1115008 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0359. Min Act: -0.0003

Data Index: 938135 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0353. Min Act: -0.0003

Data Index: 693014 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0354. Min Act: -0.0003

Data Index: 800024 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0355. Min Act: -0.0002

Data Index: 15098 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0344. Min Act: -0.0004

Data Index: 1317807 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0347. Min Act: -0.0003

Data Index: 95287 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0348. Min Act: -0.0002

Data Index: 1020543 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0364. Min Act: -0.0003

Data Index: 1204941 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0354. Min Act: -0.0002

Data Index: 1654002 (Python Code)

Max Activating Token Index: 940

Text #19

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0330. Min Act: -0.0004

Data Index: 300515 (C4 (Web Text))

Max Activating Token Index: 670