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

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

Neuron 6086 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.9536. Min Act: -0.0001

Data Index: 426943 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.8863. Min Act: -0.0001

Data Index: 399300 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.8746. Min Act: -0.0001

Data Index: 1241879 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.8697. Min Act: -0.0001

Data Index: 134360 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.8827. Min Act: -0.0001

Data Index: 1268210 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.8589. Min Act: -0.0001

Data Index: 1222526 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.8436. Min Act: -0.0001

Data Index: 916641 (C4 (Web Text))

Max Activating Token Index: 321

Text #7

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.8318. Min Act: -0.0001

Data Index: 770129 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.7327. Min Act: -0.0001

Data Index: 419869 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.8177. Min Act: -0.0001

Data Index: 977034 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.8194. Min Act: -0.0001

Data Index: 133713 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.7981. Min Act: -0.0001

Data Index: 157816 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.7775. Min Act: -0.0001

Data Index: 1283742 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.7727. Min Act: -0.0001

Data Index: 1175627 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.7465. Min Act: -0.0001

Data Index: 780273 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.7399. Min Act: -0.0001

Data Index: 341531 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.7528. Min Act: -0.0001

Data Index: 409988 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.7330. Min Act: -0.0001

Data Index: 55907 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.7514. Min Act: -0.0001

Data Index: 134219 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.6819. Min Act: -0.0001

Data Index: 673811 (C4 (Web Text))

Max Activating Token Index: 322