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

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

Neuron 2180 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.7563. Min Act: -0.0001

Data Index: 359500 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.6428. Min Act: -0.0001

Data Index: 622117 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.5644. Min Act: -0.0001

Data Index: 1154601 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.5740. Min Act: -0.0001

Data Index: 217846 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.6243. Min Act: -0.0001

Data Index: 519400 (C4 (Web Text))

Max Activating Token Index: 1019

Text #5

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.5191. Min Act: -0.0001

Data Index: 990307 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.5340. Min Act: -0.0001

Data Index: 639417 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.5214. Min Act: -0.0001

Data Index: 573468 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.5534. Min Act: -0.0001

Data Index: 305271 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.5138. Min Act: -0.0001

Data Index: 1319683 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.4979. Min Act: -0.0001

Data Index: 949969 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.5107. Min Act: -0.0001

Data Index: 387514 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.5637. Min Act: -0.0001

Data Index: 731262 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.5225. Min Act: -0.0001

Data Index: 1113560 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.4973. Min Act: -0.0001

Data Index: 664531 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.5320. Min Act: -0.0001

Data Index: 626105 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.5523. Min Act: -0.0001

Data Index: 1298536 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.5056. Min Act: -0.0001

Data Index: 67857 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.4881. Min Act: -0.0001

Data Index: 796421 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.4909. Min Act: -0.0001

Data Index: 934555 (C4 (Web Text))

Max Activating Token Index: 826