Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2070 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.5555. Min Range: -2.5555

Max Act: 2.5555. Min Act: -0.0000

Data Index: 1236371 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 2.5555. Min Range: -2.5555

Max Act: 1.9521. Min Act: -0.0001

Data Index: 302298 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 2.5555. Min Range: -2.5555

Max Act: 2.0585. Min Act: -0.0000

Data Index: 373980 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 2.5555. Min Range: -2.5555

Max Act: 2.0459. Min Act: -0.0000

Data Index: 689845 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 2.5555. Min Range: -2.5555

Max Act: 2.0466. Min Act: -0.0000

Data Index: 741988 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 2.5555. Min Range: -2.5555

Max Act: 2.1267. Min Act: -0.0000

Data Index: 748358 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 2.5555. Min Range: -2.5555

Max Act: 1.9160. Min Act: -0.0000

Data Index: 689019 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 2.5555. Min Range: -2.5555

Max Act: 2.0424. Min Act: -0.0000

Data Index: 147157 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 2.5555. Min Range: -2.5555

Max Act: 1.8249. Min Act: -0.0000

Data Index: 756407 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 2.5555. Min Range: -2.5555

Max Act: 2.0175. Min Act: -0.0000

Data Index: 489102 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 2.5555. Min Range: -2.5555

Max Act: 1.7707. Min Act: -0.0000

Data Index: 728152 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 2.5555. Min Range: -2.5555

Max Act: 1.6779. Min Act: -0.0000

Data Index: 912291 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 2.5555. Min Range: -2.5555

Max Act: 1.8880. Min Act: -0.0000

Data Index: 190831 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 2.5555. Min Range: -2.5555

Max Act: 1.6534. Min Act: -0.0000

Data Index: 674847 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 2.5555. Min Range: -2.5555

Max Act: 1.7486. Min Act: -0.0000

Data Index: 433445 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 2.5555. Min Range: -2.5555

Max Act: 1.6503. Min Act: -0.0000

Data Index: 616537 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 2.5555. Min Range: -2.5555

Max Act: 1.7362. Min Act: -0.0000

Data Index: 583524 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 2.5555. Min Range: -2.5555

Max Act: 1.7352. Min Act: -0.0000

Data Index: 850778 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 2.5555. Min Range: -2.5555

Max Act: 1.8042. Min Act: -0.0000

Data Index: 1326272 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 2.5555. Min Range: -2.5555

Max Act: 1.5133. Min Act: -0.0000

Data Index: 715235 (C4 (Web Text))

Max Activating Token Index: 928