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

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

Neuron 1635 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: 5.3488. Min Range: -5.3488

Max Act: 5.3488. Min Act: -0.0000

Data Index: 1080573 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 5.3488. Min Range: -5.3488

Max Act: 5.3470. Min Act: -0.0000

Data Index: 246184 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 5.3488. Min Range: -5.3488

Max Act: 5.1551. Min Act: -0.0000

Data Index: 1350755 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 5.3488. Min Range: -5.3488

Max Act: 4.8880. Min Act: -0.0000

Data Index: 639356 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 5.3488. Min Range: -5.3488

Max Act: 4.9771. Min Act: -0.0000

Data Index: 302198 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 5.3488. Min Range: -5.3488

Max Act: 4.2534. Min Act: -0.0000

Data Index: 1257340 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 5.3488. Min Range: -5.3488

Max Act: 4.4096. Min Act: -0.0000

Data Index: 938285 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 5.3488. Min Range: -5.3488

Max Act: 4.1725. Min Act: -0.0000

Data Index: 565577 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 5.3488. Min Range: -5.3488

Max Act: 4.1292. Min Act: -0.0000

Data Index: 390189 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 5.3488. Min Range: -5.3488

Max Act: 4.0186. Min Act: -0.0000

Data Index: 1243615 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 5.3488. Min Range: -5.3488

Max Act: 4.1464. Min Act: -0.0000

Data Index: 1273288 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 5.3488. Min Range: -5.3488

Max Act: 4.1355. Min Act: -0.0000

Data Index: 719104 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 5.3488. Min Range: -5.3488

Max Act: 3.9271. Min Act: -0.0000

Data Index: 232463 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 5.3488. Min Range: -5.3488

Max Act: 3.9678. Min Act: -0.0000

Data Index: 260616 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 5.3488. Min Range: -5.3488

Max Act: 3.9610. Min Act: -0.0000

Data Index: 622532 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 5.3488. Min Range: -5.3488

Max Act: 3.9115. Min Act: -0.0000

Data Index: 150253 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 5.3488. Min Range: -5.3488

Max Act: 4.0579. Min Act: -0.0000

Data Index: 760300 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 5.3488. Min Range: -5.3488

Max Act: 3.8539. Min Act: -0.0000

Data Index: 1021930 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 5.3488. Min Range: -5.3488

Max Act: 3.8169. Min Act: -0.0000

Data Index: 156772 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 5.3488. Min Range: -5.3488

Max Act: 3.7312. Min Act: -0.0000

Data Index: 373643 (C4 (Web Text))

Max Activating Token Index: 965