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

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

Neuron 4470 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0383. Min Range: -3.0383

Max Act: 3.0383. Min Act: -0.0000

Data Index: 1071095 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 3.0383. Min Range: -3.0383

Max Act: 1.6980. Min Act: -0.0000

Data Index: 117969 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 3.0383. Min Range: -3.0383

Max Act: 1.0949. Min Act: -0.0000

Data Index: 959952 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 3.0383. Min Range: -3.0383

Max Act: 1.0292. Min Act: -0.0000

Data Index: 908118 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 3.0383. Min Range: -3.0383

Max Act: 1.0010. Min Act: -0.0000

Data Index: 751763 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 3.0383. Min Range: -3.0383

Max Act: 0.9227. Min Act: -0.0000

Data Index: 426494 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 3.0383. Min Range: -3.0383

Max Act: 0.9554. Min Act: -0.0000

Data Index: 494804 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 3.0383. Min Range: -3.0383

Max Act: 0.8009. Min Act: -0.0000

Data Index: 735527 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 3.0383. Min Range: -3.0383

Max Act: 0.7602. Min Act: -0.0000

Data Index: 293542 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 3.0383. Min Range: -3.0383

Max Act: 0.7387. Min Act: -0.0000

Data Index: 268765 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 3.0383. Min Range: -3.0383

Max Act: 0.7626. Min Act: -0.0000

Data Index: 106151 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 3.0383. Min Range: -3.0383

Max Act: 0.7332. Min Act: -0.0000

Data Index: 1272365 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 3.0383. Min Range: -3.0383

Max Act: 0.6796. Min Act: -0.0000

Data Index: 1321153 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 3.0383. Min Range: -3.0383

Max Act: 0.7325. Min Act: -0.0000

Data Index: 1200754 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 3.0383. Min Range: -3.0383

Max Act: 0.7111. Min Act: -0.0000

Data Index: 632713 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 3.0383. Min Range: -3.0383

Max Act: 0.6576. Min Act: -0.0000

Data Index: 11877 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 3.0383. Min Range: -3.0383

Max Act: 0.6501. Min Act: -0.0000

Data Index: 16129 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 3.0383. Min Range: -3.0383

Max Act: 0.6400. Min Act: -0.0000

Data Index: 961749 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 3.0383. Min Range: -3.0383

Max Act: 0.6079. Min Act: -0.0000

Data Index: 1523160 (Python Code)

Max Activating Token Index: 470

Text #19

Max Range: 3.0383. Min Range: -3.0383

Max Act: 0.6089. Min Act: -0.0000

Data Index: 506587 (C4 (Web Text))

Max Activating Token Index: 875