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

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

Neuron 5070 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: 0.6762. Min Range: -0.6762

Max Act: 0.6600. Min Act: -0.0000

Data Index: 864260 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.6762. Min Act: -0.0000

Data Index: 1120806 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5880. Min Act: -0.0000

Data Index: 1164671 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5655. Min Act: -0.0000

Data Index: 259 (C4 (Web Text))

Max Activating Token Index: 198

Text #4

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5629. Min Act: -0.0000

Data Index: 982735 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5278. Min Act: -0.0000

Data Index: 238727 (C4 (Web Text))

Max Activating Token Index: 449

Text #6

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5520. Min Act: -0.0000

Data Index: 511481 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5365. Min Act: -0.0000

Data Index: 363209 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5299. Min Act: -0.0000

Data Index: 1321303 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.4934. Min Act: -0.0000

Data Index: 879813 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5056. Min Act: -0.0000

Data Index: 529748 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5015. Min Act: -0.0000

Data Index: 684249 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5037. Min Act: -0.0000

Data Index: 179378 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5108. Min Act: -0.0000

Data Index: 1174322 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.4803. Min Act: -0.0000

Data Index: 490095 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.4750. Min Act: -0.0000

Data Index: 9970 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5097. Min Act: -0.0000

Data Index: 1219494 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5202. Min Act: -0.0000

Data Index: 476326 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.4739. Min Act: -0.0000

Data Index: 659933 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.4855. Min Act: -0.0000

Data Index: 734204 (C4 (Web Text))

Max Activating Token Index: 110