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

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

Neuron 483 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1533. Min Act: -0.0001

Data Index: 49294 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1480. Min Act: -0.0001

Data Index: 1162322 (C4 (Web Text))

Max Activating Token Index: 1013

Text #2

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1303. Min Act: -0.0001

Data Index: 559214 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1282. Min Act: -0.0001

Data Index: 1216716 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1305. Min Act: -0.0001

Data Index: 295493 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1187. Min Act: -0.0001

Data Index: 585906 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1518. Min Act: -0.0001

Data Index: 92547 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1130. Min Act: -0.0001

Data Index: 570263 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1079. Min Act: -0.0001

Data Index: 671433 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1142. Min Act: -0.0001

Data Index: 578968 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1066. Min Act: -0.0001

Data Index: 619727 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1038. Min Act: -0.0001

Data Index: 153509 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1021. Min Act: -0.0001

Data Index: 996630 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.0993. Min Act: -0.0001

Data Index: 142646 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1035. Min Act: -0.0001

Data Index: 1291964 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.0968. Min Act: -0.0001

Data Index: 444820 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1065. Min Act: -0.0001

Data Index: 529958 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.0991. Min Act: -0.0001

Data Index: 988937 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.0990. Min Act: -0.0001

Data Index: 1358318 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.0950. Min Act: -0.0001

Data Index: 266010 (C4 (Web Text))

Max Activating Token Index: 645