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

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

Neuron 956 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: 2.4042. Min Range: -2.4042

Max Act: 2.4042. Min Act: -0.0000

Data Index: 1058652 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 2.4042. Min Range: -2.4042

Max Act: 1.9612. Min Act: -0.0000

Data Index: 719233 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 2.4042. Min Range: -2.4042

Max Act: 1.9492. Min Act: -0.0000

Data Index: 1011134 (C4 (Web Text))

Max Activating Token Index: 368

Text #3

Max Range: 2.4042. Min Range: -2.4042

Max Act: 1.8332. Min Act: -0.0000

Data Index: 278974 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 2.4042. Min Range: -2.4042

Max Act: 1.8127. Min Act: -0.0000

Data Index: 1012617 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 2.4042. Min Range: -2.4042

Max Act: 1.8079. Min Act: -0.0000

Data Index: 1356157 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 2.4042. Min Range: -2.4042

Max Act: 1.7036. Min Act: -0.0000

Data Index: 1476915 (Python Code)

Max Activating Token Index: 401

Text #7

Max Range: 2.4042. Min Range: -2.4042

Max Act: 1.5207. Min Act: -0.0000

Data Index: 891296 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 2.4042. Min Range: -2.4042

Max Act: 1.6180. Min Act: -0.0000

Data Index: 103691 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 2.4042. Min Range: -2.4042

Max Act: 1.5635. Min Act: -0.0000

Data Index: 1510843 (Python Code)

Max Activating Token Index: 695

Text #10

Max Range: 2.4042. Min Range: -2.4042

Max Act: 1.5076. Min Act: -0.0000

Data Index: 1350513 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 2.4042. Min Range: -2.4042

Max Act: 1.6231. Min Act: -0.0000

Data Index: 7624 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 2.4042. Min Range: -2.4042

Max Act: 1.5199. Min Act: -0.0000

Data Index: 897286 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 2.4042. Min Range: -2.4042

Max Act: 1.4716. Min Act: -0.0000

Data Index: 1326557 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 2.4042. Min Range: -2.4042

Max Act: 1.4694. Min Act: -0.0000

Data Index: 169497 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 2.4042. Min Range: -2.4042

Max Act: 1.2461. Min Act: -0.0000

Data Index: 1411262 (Python Code)

Max Activating Token Index: 462

Text #16

Max Range: 2.4042. Min Range: -2.4042

Max Act: 1.4907. Min Act: -0.0000

Data Index: 1351532 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 2.4042. Min Range: -2.4042

Max Act: 1.4904. Min Act: -0.0000

Data Index: 606548 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 2.4042. Min Range: -2.4042

Max Act: 1.5294. Min Act: -0.0000

Data Index: 118141 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 2.4042. Min Range: -2.4042

Max Act: 1.4008. Min Act: -0.0000

Data Index: 112020 (C4 (Web Text))

Max Activating Token Index: 302