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

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

Neuron 546 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0622. Min Act: -0.0001

Data Index: 1385986 (Python Code)

Max Activating Token Index: 811

Text #1

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0554. Min Act: -0.0001

Data Index: 871203 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0535. Min Act: -0.0001

Data Index: 1557234 (Python Code)

Max Activating Token Index: 161

Text #3

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0527. Min Act: -0.0001

Data Index: 548130 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0528. Min Act: -0.0001

Data Index: 459671 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0475. Min Act: -0.0001

Data Index: 1004166 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0483. Min Act: -0.0001

Data Index: 490411 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0497. Min Act: -0.0001

Data Index: 234970 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0451. Min Act: -0.0001

Data Index: 1507047 (Python Code)

Max Activating Token Index: 71

Text #9

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0470. Min Act: -0.0001

Data Index: 974269 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0465. Min Act: -0.0001

Data Index: 723324 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0459. Min Act: -0.0001

Data Index: 1058685 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0476. Min Act: -0.0001

Data Index: 1627515 (Python Code)

Max Activating Token Index: 171

Text #13

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0465. Min Act: -0.0001

Data Index: 1654275 (Python Code)

Max Activating Token Index: 84

Text #14

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0448. Min Act: -0.0001

Data Index: 403364 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0463. Min Act: -0.0001

Data Index: 390845 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0461. Min Act: -0.0001

Data Index: 181953 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0446. Min Act: -0.0001

Data Index: 280374 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0444. Min Act: -0.0001

Data Index: 774950 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0443. Min Act: -0.0001

Data Index: 1431860 (Python Code)

Max Activating Token Index: 73