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

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

Neuron 1390 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0465. Min Act: -0.0004

Data Index: 805587 (C4 (Web Text))

Max Activating Token Index: 599

Text #1

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0544. Min Act: -0.0004

Data Index: 135159 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0542. Min Act: -0.0004

Data Index: 201947 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0488. Min Act: -0.0004

Data Index: 296060 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0501. Min Act: -0.0004

Data Index: 984769 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0506. Min Act: -0.0004

Data Index: 1384751 (Python Code)

Max Activating Token Index: 697

Text #6

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0447. Min Act: -0.0004

Data Index: 398628 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0512. Min Act: -0.0004

Data Index: 402327 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0497. Min Act: -0.0004

Data Index: 949375 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0492. Min Act: -0.0004

Data Index: 826626 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0473. Min Act: -0.0004

Data Index: 117558 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0444. Min Act: -0.0004

Data Index: 758886 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0468. Min Act: -0.0004

Data Index: 369381 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0449. Min Act: -0.0004

Data Index: 1507139 (Python Code)

Max Activating Token Index: 9

Text #14

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0453. Min Act: -0.0004

Data Index: 174006 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0462. Min Act: -0.0004

Data Index: 1101947 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0442. Min Act: -0.0004

Data Index: 1148770 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0455. Min Act: -0.0004

Data Index: 988051 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0404. Min Act: -0.0004

Data Index: 1243018 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0445. Min Act: -0.0004

Data Index: 929677 (C4 (Web Text))

Max Activating Token Index: 16