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

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

Neuron 337 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.6585. Min Act: -0.0000

Data Index: 494650 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.6648. Min Act: -0.0000

Data Index: 1060852 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.6431. Min Act: -0.0000

Data Index: 425505 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5893. Min Act: -0.0000

Data Index: 507109 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5591. Min Act: -0.0000

Data Index: 540671 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5685. Min Act: -0.0000

Data Index: 384355 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5790. Min Act: -0.0000

Data Index: 505391 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5442. Min Act: 0.0000

Data Index: 1176553 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5367. Min Act: -0.0000

Data Index: 1154374 (C4 (Web Text))

Max Activating Token Index: 687

Text #9

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5337. Min Act: -0.0000

Data Index: 328279 (C4 (Web Text))

Max Activating Token Index: 684

Text #10

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5189. Min Act: -0.0000

Data Index: 789705 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5329. Min Act: -0.0000

Data Index: 132937 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5311. Min Act: -0.0000

Data Index: 381595 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5248. Min Act: -0.0000

Data Index: 621646 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4856. Min Act: -0.0000

Data Index: 974535 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4747. Min Act: 0.0000

Data Index: 786521 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4934. Min Act: -0.0000

Data Index: 389490 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4613. Min Act: -0.0000

Data Index: 669064 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4608. Min Act: -0.0000

Data Index: 440017 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4831. Min Act: -0.0000

Data Index: 796557 (C4 (Web Text))

Max Activating Token Index: 106