Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2778 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2501. Min Range: -1.2501

Max Act: 1.1445. Min Act: -0.0002

Data Index: 734967 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 1.2501. Min Range: -1.2501

Max Act: 1.1708. Min Act: -0.0001

Data Index: 922287 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 1.2501. Min Range: -1.2501

Max Act: 1.2501. Min Act: -0.0001

Data Index: 346347 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 1.2501. Min Range: -1.2501

Max Act: 1.0100. Min Act: -0.0001

Data Index: 1094844 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 1.2501. Min Range: -1.2501

Max Act: 1.1152. Min Act: -0.0001

Data Index: 925515 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 1.2501. Min Range: -1.2501

Max Act: 0.9392. Min Act: -0.0002

Data Index: 273453 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 1.2501. Min Range: -1.2501

Max Act: 0.9914. Min Act: -0.0002

Data Index: 338665 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 1.2501. Min Range: -1.2501

Max Act: 0.9597. Min Act: -0.0002

Data Index: 966011 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 1.2501. Min Range: -1.2501

Max Act: 0.9263. Min Act: -0.0002

Data Index: 1240848 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 1.2501. Min Range: -1.2501

Max Act: 0.9143. Min Act: -0.0002

Data Index: 447085 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 1.2501. Min Range: -1.2501

Max Act: 0.9577. Min Act: -0.0002

Data Index: 259970 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 1.2501. Min Range: -1.2501

Max Act: 0.9512. Min Act: -0.0002

Data Index: 2829 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 1.2501. Min Range: -1.2501

Max Act: 0.9396. Min Act: -0.0001

Data Index: 15334 (C4 (Web Text))

Max Activating Token Index: 525

Text #13

Max Range: 1.2501. Min Range: -1.2501

Max Act: 0.8569. Min Act: -0.0001

Data Index: 582462 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 1.2501. Min Range: -1.2501

Max Act: 0.8959. Min Act: -0.0002

Data Index: 233317 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 1.2501. Min Range: -1.2501

Max Act: 0.9449. Min Act: -0.0002

Data Index: 204188 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 1.2501. Min Range: -1.2501

Max Act: 0.8800. Min Act: -0.0002

Data Index: 484236 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 1.2501. Min Range: -1.2501

Max Act: 0.9666. Min Act: -0.0002

Data Index: 392014 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 1.2501. Min Range: -1.2501

Max Act: 0.8845. Min Act: -0.0002

Data Index: 1158289 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 1.2501. Min Range: -1.2501

Max Act: 0.9007. Min Act: -0.0001

Data Index: 488474 (C4 (Web Text))

Max Activating Token Index: 53