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

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

Neuron 3871 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.1406. Min Range: -4.1406

Max Act: 4.0262. Min Act: -0.0000

Data Index: 468072 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 4.1406. Min Range: -4.1406

Max Act: 4.1406. Min Act: -0.0000

Data Index: 1290366 (C4 (Web Text))

Max Activating Token Index: 592

Text #2

Max Range: 4.1406. Min Range: -4.1406

Max Act: 3.8940. Min Act: -0.0000

Data Index: 803339 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 4.1406. Min Range: -4.1406

Max Act: 3.8174. Min Act: -0.0000

Data Index: 458989 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 4.1406. Min Range: -4.1406

Max Act: 3.3867. Min Act: -0.0000

Data Index: 357883 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 4.1406. Min Range: -4.1406

Max Act: 3.2426. Min Act: -0.0000

Data Index: 334393 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 4.1406. Min Range: -4.1406

Max Act: 3.0838. Min Act: -0.0000

Data Index: 48731 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 4.1406. Min Range: -4.1406

Max Act: 3.3780. Min Act: -0.0000

Data Index: 1323071 (C4 (Web Text))

Max Activating Token Index: 448

Text #8

Max Range: 4.1406. Min Range: -4.1406

Max Act: 3.1482. Min Act: -0.0000

Data Index: 981656 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 4.1406. Min Range: -4.1406

Max Act: 3.3064. Min Act: -0.0000

Data Index: 269138 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 4.1406. Min Range: -4.1406

Max Act: 3.1438. Min Act: -0.0000

Data Index: 368197 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 4.1406. Min Range: -4.1406

Max Act: 3.4976. Min Act: -0.0000

Data Index: 1342988 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 4.1406. Min Range: -4.1406

Max Act: 3.2958. Min Act: -0.0000

Data Index: 254179 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 4.1406. Min Range: -4.1406

Max Act: 3.2378. Min Act: -0.0000

Data Index: 131271 (C4 (Web Text))

Max Activating Token Index: 491

Text #14

Max Range: 4.1406. Min Range: -4.1406

Max Act: 3.1318. Min Act: -0.0000

Data Index: 578313 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 4.1406. Min Range: -4.1406

Max Act: 3.3038. Min Act: -0.0000

Data Index: 986780 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 4.1406. Min Range: -4.1406

Max Act: 3.1540. Min Act: -0.0000

Data Index: 986064 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 4.1406. Min Range: -4.1406

Max Act: 3.1810. Min Act: -0.0000

Data Index: 460189 (C4 (Web Text))

Max Activating Token Index: 777

Text #18

Max Range: 4.1406. Min Range: -4.1406

Max Act: 2.8665. Min Act: -0.0000

Data Index: 225363 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 4.1406. Min Range: -4.1406

Max Act: 3.1407. Min Act: -0.0000

Data Index: 231339 (C4 (Web Text))

Max Activating Token Index: 656