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

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

Neuron 2284 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7587. Min Range: -2.7587

Max Act: 2.7587. Min Act: -0.0000

Data Index: 72265 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 2.7587. Min Range: -2.7587

Max Act: 2.1410. Min Act: -0.0000

Data Index: 294011 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 2.7587. Min Range: -2.7587

Max Act: 2.3455. Min Act: -0.0000

Data Index: 985863 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 2.7587. Min Range: -2.7587

Max Act: 2.3149. Min Act: -0.0000

Data Index: 822264 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 2.7587. Min Range: -2.7587

Max Act: 2.1462. Min Act: -0.0000

Data Index: 487527 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 2.7587. Min Range: -2.7587

Max Act: 1.7417. Min Act: -0.0000

Data Index: 825568 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 2.7587. Min Range: -2.7587

Max Act: 1.8301. Min Act: -0.0000

Data Index: 131835 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 2.7587. Min Range: -2.7587

Max Act: 1.7537. Min Act: -0.0000

Data Index: 919684 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 2.7587. Min Range: -2.7587

Max Act: 1.9227. Min Act: -0.0000

Data Index: 838557 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 2.7587. Min Range: -2.7587

Max Act: 1.7953. Min Act: -0.0000

Data Index: 1301498 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 2.7587. Min Range: -2.7587

Max Act: 1.8048. Min Act: -0.0000

Data Index: 215492 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 2.7587. Min Range: -2.7587

Max Act: 1.8415. Min Act: -0.0000

Data Index: 213382 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 2.7587. Min Range: -2.7587

Max Act: 1.8405. Min Act: -0.0000

Data Index: 434809 (C4 (Web Text))

Max Activating Token Index: 630

Text #13

Max Range: 2.7587. Min Range: -2.7587

Max Act: 1.7624. Min Act: -0.0000

Data Index: 843457 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 2.7587. Min Range: -2.7587

Max Act: 1.8467. Min Act: -0.0000

Data Index: 479584 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 2.7587. Min Range: -2.7587

Max Act: 1.7460. Min Act: -0.0000

Data Index: 1125876 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 2.7587. Min Range: -2.7587

Max Act: 1.7290. Min Act: -0.0000

Data Index: 898108 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 2.7587. Min Range: -2.7587

Max Act: 1.8343. Min Act: -0.0000

Data Index: 234751 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 2.7587. Min Range: -2.7587

Max Act: 1.7006. Min Act: -0.0000

Data Index: 46351 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 2.7587. Min Range: -2.7587

Max Act: 1.7012. Min Act: -0.0000

Data Index: 997496 (C4 (Web Text))

Max Activating Token Index: 74