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

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

Neuron 1493 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6716. Min Range: -1.6716

Max Act: 1.6716. Min Act: -0.0001

Data Index: 1315342 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 1.6716. Min Range: -1.6716

Max Act: 1.5969. Min Act: -0.0001

Data Index: 868118 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 1.6716. Min Range: -1.6716

Max Act: 1.4773. Min Act: -0.0001

Data Index: 120547 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 1.6716. Min Range: -1.6716

Max Act: 1.5426. Min Act: -0.0001

Data Index: 934351 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 1.6716. Min Range: -1.6716

Max Act: 1.3699. Min Act: -0.0001

Data Index: 403716 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 1.6716. Min Range: -1.6716

Max Act: 1.3442. Min Act: -0.0001

Data Index: 734783 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 1.6716. Min Range: -1.6716

Max Act: 1.3295. Min Act: -0.0001

Data Index: 114031 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 1.6716. Min Range: -1.6716

Max Act: 1.3341. Min Act: -0.0001

Data Index: 160893 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 1.6716. Min Range: -1.6716

Max Act: 1.2077. Min Act: -0.0001

Data Index: 791541 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 1.6716. Min Range: -1.6716

Max Act: 1.3278. Min Act: -0.0001

Data Index: 985147 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 1.6716. Min Range: -1.6716

Max Act: 1.3198. Min Act: -0.0001

Data Index: 787096 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 1.6716. Min Range: -1.6716

Max Act: 1.2904. Min Act: -0.0001

Data Index: 226080 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 1.6716. Min Range: -1.6716

Max Act: 1.2419. Min Act: -0.0001

Data Index: 914321 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 1.6716. Min Range: -1.6716

Max Act: 1.2405. Min Act: -0.0001

Data Index: 842506 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 1.6716. Min Range: -1.6716

Max Act: 1.2713. Min Act: -0.0001

Data Index: 739701 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 1.6716. Min Range: -1.6716

Max Act: 1.1577. Min Act: -0.0001

Data Index: 760601 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 1.6716. Min Range: -1.6716

Max Act: 1.2364. Min Act: -0.0001

Data Index: 1314764 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 1.6716. Min Range: -1.6716

Max Act: 1.1462. Min Act: -0.0001

Data Index: 1069528 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 1.6716. Min Range: -1.6716

Max Act: 1.1731. Min Act: -0.0001

Data Index: 824322 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 1.6716. Min Range: -1.6716

Max Act: 1.2030. Min Act: -0.0001

Data Index: 736528 (C4 (Web Text))

Max Activating Token Index: 682