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

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

Neuron 4298 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0762. Min Range: -1.0762

Max Act: 1.0762. Min Act: -0.0000

Data Index: 392324 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 1.0762. Min Range: -1.0762

Max Act: 1.0672. Min Act: -0.0000

Data Index: 205214 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 1.0762. Min Range: -1.0762

Max Act: 1.0167. Min Act: -0.0000

Data Index: 1236445 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.9759. Min Act: -0.0000

Data Index: 1228318 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.9837. Min Act: -0.0000

Data Index: 147088 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.9826. Min Act: -0.0000

Data Index: 1092548 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.9447. Min Act: -0.0000

Data Index: 639941 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.9957. Min Act: -0.0000

Data Index: 1141863 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.9516. Min Act: -0.0000

Data Index: 40041 (C4 (Web Text))

Max Activating Token Index: 628

Text #9

Max Range: 1.0762. Min Range: -1.0762

Max Act: 1.0752. Min Act: -0.0000

Data Index: 336816 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.9062. Min Act: -0.0000

Data Index: 1294398 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.9441. Min Act: -0.0000

Data Index: 643938 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.9150. Min Act: -0.0000

Data Index: 682818 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.8935. Min Act: -0.0000

Data Index: 819155 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.8437. Min Act: -0.0000

Data Index: 506626 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.8515. Min Act: -0.0000

Data Index: 1049693 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.8689. Min Act: -0.0000

Data Index: 285791 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.8294. Min Act: -0.0000

Data Index: 693996 (C4 (Web Text))

Max Activating Token Index: 633

Text #18

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.8996. Min Act: -0.0000

Data Index: 519954 (C4 (Web Text))

Max Activating Token Index: 602

Text #19

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.8639. Min Act: -0.0000

Data Index: 1183991 (C4 (Web Text))

Max Activating Token Index: 753