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

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

Neuron 1092 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0948. Min Range: -1.0948

Max Act: 1.0948. Min Act: -0.0000

Data Index: 1086936 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 1.0948. Min Range: -1.0948

Max Act: 1.0224. Min Act: -0.0000

Data Index: 1241013 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.9109. Min Act: -0.0000

Data Index: 1111534 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.8386. Min Act: -0.0000

Data Index: 803443 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.8442. Min Act: -0.0000

Data Index: 124211 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.8817. Min Act: -0.0000

Data Index: 670793 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.8692. Min Act: -0.0000

Data Index: 791819 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.8407. Min Act: -0.0000

Data Index: 1259336 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.8507. Min Act: -0.0000

Data Index: 1252456 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.8435. Min Act: -0.0000

Data Index: 905334 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.8270. Min Act: -0.0000

Data Index: 888226 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.7630. Min Act: -0.0000

Data Index: 711391 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.8554. Min Act: -0.0000

Data Index: 1233250 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.7766. Min Act: -0.0000

Data Index: 1012469 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.6896. Min Act: -0.0000

Data Index: 1157479 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.6514. Min Act: -0.0000

Data Index: 90551 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.7570. Min Act: -0.0000

Data Index: 152040 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.7640. Min Act: -0.0000

Data Index: 1151774 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.7621. Min Act: -0.0000

Data Index: 1296050 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.7651. Min Act: -0.0000

Data Index: 983289 (C4 (Web Text))

Max Activating Token Index: 501