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

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

Neuron 3522 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1468. Min Act: -0.0000

Data Index: 331603 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1218. Min Act: -0.0000

Data Index: 1282764 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1079. Min Act: -0.0000

Data Index: 263632 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1210. Min Act: -0.0000

Data Index: 722416 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1099. Min Act: -0.0000

Data Index: 128922 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1093. Min Act: -0.0001

Data Index: 336096 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1056. Min Act: -0.0000

Data Index: 850689 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0985. Min Act: -0.0001

Data Index: 1028458 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1171. Min Act: -0.0000

Data Index: 632216 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0981. Min Act: -0.0001

Data Index: 533643 (C4 (Web Text))

Max Activating Token Index: 756

Text #10

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1107. Min Act: -0.0000

Data Index: 638535 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0961. Min Act: -0.0001

Data Index: 890556 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0954. Min Act: -0.0001

Data Index: 182688 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0940. Min Act: -0.0000

Data Index: 851534 (C4 (Web Text))

Max Activating Token Index: 604

Text #14

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0922. Min Act: -0.0000

Data Index: 713810 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0939. Min Act: -0.0000

Data Index: 15283 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0993. Min Act: -0.0000

Data Index: 792144 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0962. Min Act: -0.0001

Data Index: 1216809 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0871. Min Act: -0.0001

Data Index: 597145 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1062. Min Act: -0.0000

Data Index: 160649 (C4 (Web Text))

Max Activating Token Index: 624