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

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

Neuron 3407 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: 0.5054. Min Range: -0.5054

Max Act: 0.5054. Min Act: -0.0000

Data Index: 498636 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4288. Min Act: -0.0000

Data Index: 459107 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4353. Min Act: -0.0000

Data Index: 1357386 (C4 (Web Text))

Max Activating Token Index: 488

Text #3

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4101. Min Act: -0.0000

Data Index: 1335351 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3727. Min Act: -0.0000

Data Index: 717076 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3638. Min Act: -0.0000

Data Index: 528474 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3794. Min Act: -0.0000

Data Index: 1202465 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3866. Min Act: -0.0000

Data Index: 467613 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4229. Min Act: -0.0000

Data Index: 1259580 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3490. Min Act: -0.0000

Data Index: 791542 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3521. Min Act: -0.0000

Data Index: 59901 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3539. Min Act: -0.0000

Data Index: 465347 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3140. Min Act: -0.0000

Data Index: 694550 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3165. Min Act: -0.0000

Data Index: 56561 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.2902. Min Act: -0.0000

Data Index: 88612 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.2895. Min Act: -0.0000

Data Index: 893694 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.2949. Min Act: -0.0000

Data Index: 592715 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.2929. Min Act: -0.0000

Data Index: 494083 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.2788. Min Act: -0.0000

Data Index: 995152 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.2749. Min Act: -0.0000

Data Index: 959275 (C4 (Web Text))

Max Activating Token Index: 606