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

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

Neuron 2702 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8571. Min Range: -1.8571

Max Act: 1.8571. Min Act: -0.0001

Data Index: 880252 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 1.8571. Min Range: -1.8571

Max Act: 1.5548. Min Act: -0.0001

Data Index: 1425172 (Python Code)

Max Activating Token Index: 146

Text #2

Max Range: 1.8571. Min Range: -1.8571

Max Act: 1.5260. Min Act: -0.0001

Data Index: 600193 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 1.8571. Min Range: -1.8571

Max Act: 1.4296. Min Act: -0.0000

Data Index: 1171681 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 1.8571. Min Range: -1.8571

Max Act: 1.5884. Min Act: -0.0001

Data Index: 300295 (C4 (Web Text))

Max Activating Token Index: 939

Text #5

Max Range: 1.8571. Min Range: -1.8571

Max Act: 1.5857. Min Act: -0.0001

Data Index: 67107 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 1.8571. Min Range: -1.8571

Max Act: 1.4868. Min Act: -0.0001

Data Index: 940129 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 1.8571. Min Range: -1.8571

Max Act: 1.2715. Min Act: -0.0000

Data Index: 22169 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 1.8571. Min Range: -1.8571

Max Act: 1.4383. Min Act: -0.0001

Data Index: 642528 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 1.8571. Min Range: -1.8571

Max Act: 1.3418. Min Act: -0.0001

Data Index: 251390 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 1.8571. Min Range: -1.8571

Max Act: 1.1403. Min Act: -0.0001

Data Index: 1143763 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 1.8571. Min Range: -1.8571

Max Act: 1.3001. Min Act: -0.0001

Data Index: 885912 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 1.8571. Min Range: -1.8571

Max Act: 1.2502. Min Act: -0.0001

Data Index: 885644 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 1.8571. Min Range: -1.8571

Max Act: 1.3134. Min Act: -0.0001

Data Index: 537111 (C4 (Web Text))

Max Activating Token Index: 412

Text #14

Max Range: 1.8571. Min Range: -1.8571

Max Act: 1.2437. Min Act: -0.0000

Data Index: 746161 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 1.8571. Min Range: -1.8571

Max Act: 1.2564. Min Act: -0.0001

Data Index: 1118237 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 1.8571. Min Range: -1.8571

Max Act: 1.1305. Min Act: -0.0001

Data Index: 263267 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 1.8571. Min Range: -1.8571

Max Act: 1.1913. Min Act: -0.0001

Data Index: 226762 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 1.8571. Min Range: -1.8571

Max Act: 1.1434. Min Act: -0.0001

Data Index: 919081 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 1.8571. Min Range: -1.8571

Max Act: 1.0707. Min Act: -0.0001

Data Index: 956780 (C4 (Web Text))

Max Activating Token Index: 941