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

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

Neuron 642 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7092. Min Range: -2.7092

Max Act: 2.7092. Min Act: -0.0000

Data Index: 786670 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 2.7092. Min Range: -2.7092

Max Act: 2.5345. Min Act: -0.0000

Data Index: 188018 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 2.7092. Min Range: -2.7092

Max Act: 2.2273. Min Act: -0.0000

Data Index: 247472 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 2.7092. Min Range: -2.7092

Max Act: 2.1918. Min Act: -0.0000

Data Index: 390358 (C4 (Web Text))

Max Activating Token Index: 533

Text #4

Max Range: 2.7092. Min Range: -2.7092

Max Act: 2.0216. Min Act: -0.0000

Data Index: 638114 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 2.7092. Min Range: -2.7092

Max Act: 2.0838. Min Act: -0.0000

Data Index: 1088241 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 2.7092. Min Range: -2.7092

Max Act: 2.2374. Min Act: -0.0000

Data Index: 84284 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 2.7092. Min Range: -2.7092

Max Act: 1.9685. Min Act: -0.0000

Data Index: 948396 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 2.7092. Min Range: -2.7092

Max Act: 1.9649. Min Act: -0.0000

Data Index: 1211467 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 2.7092. Min Range: -2.7092

Max Act: 1.9691. Min Act: -0.0000

Data Index: 874854 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 2.7092. Min Range: -2.7092

Max Act: 1.9567. Min Act: -0.0000

Data Index: 907301 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 2.7092. Min Range: -2.7092

Max Act: 1.9514. Min Act: -0.0000

Data Index: 147169 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 2.7092. Min Range: -2.7092

Max Act: 2.0414. Min Act: -0.0000

Data Index: 517965 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 2.7092. Min Range: -2.7092

Max Act: 1.9426. Min Act: -0.0000

Data Index: 1270387 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 2.7092. Min Range: -2.7092

Max Act: 1.9480. Min Act: -0.0000

Data Index: 333001 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 2.7092. Min Range: -2.7092

Max Act: 1.7906. Min Act: -0.0001

Data Index: 627943 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 2.7092. Min Range: -2.7092

Max Act: 1.8763. Min Act: -0.0000

Data Index: 818621 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 2.7092. Min Range: -2.7092

Max Act: 1.8827. Min Act: -0.0000

Data Index: 807583 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 2.7092. Min Range: -2.7092

Max Act: 1.8708. Min Act: -0.0000

Data Index: 762990 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 2.7092. Min Range: -2.7092

Max Act: 1.7761. Min Act: -0.0000

Data Index: 927497 (C4 (Web Text))

Max Activating Token Index: 397