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

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

Neuron 6105 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.6992. Min Act: -0.0002

Data Index: 1343864 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.6364. Min Act: -0.0002

Data Index: 1188839 (C4 (Web Text))

Max Activating Token Index: 788

Text #2

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.6056. Min Act: -0.0002

Data Index: 302799 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.5943. Min Act: -0.0002

Data Index: 1313721 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.5900. Min Act: -0.0002

Data Index: 198006 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.5692. Min Act: -0.0002

Data Index: 1317149 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.5829. Min Act: -0.0002

Data Index: 376132 (C4 (Web Text))

Max Activating Token Index: 515

Text #7

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.5649. Min Act: -0.0002

Data Index: 638707 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.5749. Min Act: -0.0002

Data Index: 1243605 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.5611. Min Act: -0.0002

Data Index: 437444 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.5591. Min Act: -0.0002

Data Index: 1252363 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.5756. Min Act: -0.0002

Data Index: 386103 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.5529. Min Act: -0.0002

Data Index: 197304 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.5448. Min Act: -0.0002

Data Index: 693247 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.5578. Min Act: -0.0002

Data Index: 901717 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.5547. Min Act: -0.0002

Data Index: 532735 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.5511. Min Act: -0.0002

Data Index: 250223 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.5438. Min Act: -0.0002

Data Index: 1008197 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.5480. Min Act: -0.0002

Data Index: 32910 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.5233. Min Act: -0.0002

Data Index: 275626 (C4 (Web Text))

Max Activating Token Index: 441