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

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

Neuron 982 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: 0.6197. Min Range: -0.6197

Max Act: 0.6197. Min Act: -0.0001

Data Index: 1476224 (Python Code)

Max Activating Token Index: 928

Text #1

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4917. Min Act: -0.0001

Data Index: 1643298 (Python Code)

Max Activating Token Index: 1013

Text #2

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4410. Min Act: -0.0001

Data Index: 1442692 (Python Code)

Max Activating Token Index: 981

Text #3

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4626. Min Act: -0.0002

Data Index: 1369401 (Python Code)

Max Activating Token Index: 1008

Text #4

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4918. Min Act: -0.0001

Data Index: 1375484 (Python Code)

Max Activating Token Index: 863

Text #5

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4019. Min Act: -0.0001

Data Index: 1547455 (Python Code)

Max Activating Token Index: 238

Text #6

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.3459. Min Act: -0.0001

Data Index: 1481286 (Python Code)

Max Activating Token Index: 934

Text #7

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4366. Min Act: -0.0001

Data Index: 1486142 (Python Code)

Max Activating Token Index: 625

Text #8

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4772. Min Act: -0.0001

Data Index: 304839 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4410. Min Act: -0.0001

Data Index: 1385929 (Python Code)

Max Activating Token Index: 981

Text #10

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4147. Min Act: -0.0001

Data Index: 1579800 (Python Code)

Max Activating Token Index: 701

Text #11

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4234. Min Act: -0.0001

Data Index: 1558343 (Python Code)

Max Activating Token Index: 888

Text #12

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4272. Min Act: -0.0001

Data Index: 803199 (C4 (Web Text))

Max Activating Token Index: 525

Text #13

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4573. Min Act: -0.0001

Data Index: 875255 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4341. Min Act: -0.0001

Data Index: 1479862 (Python Code)

Max Activating Token Index: 205

Text #15

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.3721. Min Act: -0.0001

Data Index: 1483851 (Python Code)

Max Activating Token Index: 872

Text #16

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4529. Min Act: -0.0001

Data Index: 1610629 (Python Code)

Max Activating Token Index: 1009

Text #17

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4223. Min Act: -0.0001

Data Index: 1604880 (Python Code)

Max Activating Token Index: 1001

Text #18

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.5622. Min Act: -0.0001

Data Index: 1557270 (Python Code)

Max Activating Token Index: 730

Text #19

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4362. Min Act: -0.0001

Data Index: 1405470 (Python Code)

Max Activating Token Index: 666