Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1057 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.9565. Min Act: -0.0000

Data Index: 1277946 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 1.0495. Min Range: -1.0495

Max Act: 1.0495. Min Act: -0.0000

Data Index: 1317671 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.8337. Min Act: -0.0000

Data Index: 1212551 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.8666. Min Act: -0.0000

Data Index: 346451 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.8109. Min Act: -0.0000

Data Index: 408209 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.7779. Min Act: -0.0000

Data Index: 759528 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.7704. Min Act: -0.0000

Data Index: 583943 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.7177. Min Act: -0.0000

Data Index: 62031 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.6640. Min Act: -0.0000

Data Index: 466013 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.6366. Min Act: -0.0000

Data Index: 467322 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.5851. Min Act: -0.0000

Data Index: 1336962 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.5805. Min Act: -0.0000

Data Index: 1094382 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.5913. Min Act: -0.0000

Data Index: 1169512 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.6287. Min Act: -0.0000

Data Index: 760122 (C4 (Web Text))

Max Activating Token Index: 683

Text #14

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.5889. Min Act: -0.0000

Data Index: 1196095 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.6315. Min Act: -0.0000

Data Index: 305836 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.5449. Min Act: -0.0000

Data Index: 1077974 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.5587. Min Act: -0.0000

Data Index: 984448 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.5838. Min Act: -0.0000

Data Index: 715272 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.5595. Min Act: -0.0000

Data Index: 921594 (C4 (Web Text))

Max Activating Token Index: 577