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

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

Neuron 2790 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.5570. Min Act: -0.0003

Data Index: 621989 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.5429. Min Act: -0.0003

Data Index: 618106 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.5448. Min Act: -0.0003

Data Index: 604421 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.5034. Min Act: -0.0003

Data Index: 885169 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.5040. Min Act: -0.0003

Data Index: 486369 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.5010. Min Act: -0.0003

Data Index: 427749 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4877. Min Act: -0.0003

Data Index: 1055181 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4739. Min Act: -0.0003

Data Index: 1207106 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4600. Min Act: -0.0003

Data Index: 977678 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4523. Min Act: -0.0003

Data Index: 88629 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4682. Min Act: -0.0003

Data Index: 1035233 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4682. Min Act: -0.0003

Data Index: 418623 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4800. Min Act: -0.0003

Data Index: 596538 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4326. Min Act: -0.0003

Data Index: 50148 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4371. Min Act: -0.0003

Data Index: 1210425 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4529. Min Act: -0.0003

Data Index: 1146068 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4531. Min Act: -0.0003

Data Index: 708749 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4191. Min Act: -0.0003

Data Index: 581348 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4475. Min Act: -0.0003

Data Index: 843133 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4338. Min Act: -0.0003

Data Index: 821436 (C4 (Web Text))

Max Activating Token Index: 899