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

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

Neuron 441 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1964. Min Act: -0.0001

Data Index: 174677 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1653. Min Act: -0.0001

Data Index: 146519 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1715. Min Act: -0.0001

Data Index: 1046891 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1689. Min Act: -0.0001

Data Index: 38232 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1541. Min Act: -0.0001

Data Index: 329883 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1512. Min Act: -0.0001

Data Index: 1028973 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1555. Min Act: -0.0001

Data Index: 167804 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1538. Min Act: -0.0001

Data Index: 445693 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1516. Min Act: -0.0001

Data Index: 628417 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1372. Min Act: -0.0001

Data Index: 958598 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1421. Min Act: -0.0001

Data Index: 182123 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1403. Min Act: -0.0001

Data Index: 1027606 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1489. Min Act: -0.0001

Data Index: 235392 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1320. Min Act: -0.0001

Data Index: 1238924 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1317. Min Act: -0.0001

Data Index: 1317984 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1420. Min Act: -0.0001

Data Index: 1167866 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1313. Min Act: -0.0001

Data Index: 1125361 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1270. Min Act: -0.0001

Data Index: 294024 (C4 (Web Text))

Max Activating Token Index: 898

Text #18

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1294. Min Act: -0.0001

Data Index: 564463 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1249. Min Act: -0.0001

Data Index: 1054133 (C4 (Web Text))

Max Activating Token Index: 961