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

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

Neuron 3333 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: 0.5370. Min Range: -0.5370

Max Act: 0.5370. Min Act: -0.0000

Data Index: 680098 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4748. Min Act: -0.0000

Data Index: 1097856 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4431. Min Act: -0.0000

Data Index: 204189 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4376. Min Act: -0.0000

Data Index: 1080344 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4401. Min Act: -0.0000

Data Index: 1124326 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4107. Min Act: -0.0000

Data Index: 322546 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4099. Min Act: -0.0000

Data Index: 457805 (C4 (Web Text))

Max Activating Token Index: 931

Text #7

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3830. Min Act: -0.0000

Data Index: 904397 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4030. Min Act: -0.0000

Data Index: 165663 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3972. Min Act: -0.0000

Data Index: 480317 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3921. Min Act: -0.0000

Data Index: 67685 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3693. Min Act: 0.0000

Data Index: 854224 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3784. Min Act: -0.0000

Data Index: 278182 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3759. Min Act: 0.0000

Data Index: 229988 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3738. Min Act: -0.0000

Data Index: 1280551 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3719. Min Act: -0.0000

Data Index: 93544 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3597. Min Act: -0.0000

Data Index: 877455 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3597. Min Act: -0.0000

Data Index: 833457 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3646. Min Act: -0.0000

Data Index: 1141717 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3784. Min Act: 0.0000

Data Index: 778257 (C4 (Web Text))

Max Activating Token Index: 68