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

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

Neuron 365 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6070. Min Range: -0.6070

Max Act: 0.6070. Min Act: -0.0000

Data Index: 38066 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 0.6070. Min Range: -0.6070

Max Act: 0.5619. Min Act: -0.0000

Data Index: 971077 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 0.6070. Min Range: -0.6070

Max Act: 0.4971. Min Act: -0.0000

Data Index: 426373 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 0.6070. Min Range: -0.6070

Max Act: 0.4456. Min Act: -0.0001

Data Index: 75909 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 0.6070. Min Range: -0.6070

Max Act: 0.4824. Min Act: -0.0000

Data Index: 388474 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 0.6070. Min Range: -0.6070

Max Act: 0.4891. Min Act: -0.0000

Data Index: 672198 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 0.6070. Min Range: -0.6070

Max Act: 0.4090. Min Act: -0.0000

Data Index: 1004533 (C4 (Web Text))

Max Activating Token Index: 376

Text #7

Max Range: 0.6070. Min Range: -0.6070

Max Act: 0.4468. Min Act: -0.0000

Data Index: 523590 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 0.6070. Min Range: -0.6070

Max Act: 0.3989. Min Act: -0.0000

Data Index: 272027 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 0.6070. Min Range: -0.6070

Max Act: 0.3740. Min Act: -0.0000

Data Index: 303889 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 0.6070. Min Range: -0.6070

Max Act: 0.3704. Min Act: -0.0000

Data Index: 701017 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 0.6070. Min Range: -0.6070

Max Act: 0.3821. Min Act: -0.0000

Data Index: 998118 (C4 (Web Text))

Max Activating Token Index: 389

Text #12

Max Range: 0.6070. Min Range: -0.6070

Max Act: 0.3801. Min Act: -0.0000

Data Index: 32689 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 0.6070. Min Range: -0.6070

Max Act: 0.3958. Min Act: -0.0000

Data Index: 1018395 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 0.6070. Min Range: -0.6070

Max Act: 0.3915. Min Act: -0.0000

Data Index: 1047671 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.6070. Min Range: -0.6070

Max Act: 0.3765. Min Act: -0.0000

Data Index: 395361 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 0.6070. Min Range: -0.6070

Max Act: 0.4056. Min Act: -0.0000

Data Index: 102313 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 0.6070. Min Range: -0.6070

Max Act: 0.3630. Min Act: -0.0000

Data Index: 307150 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 0.6070. Min Range: -0.6070

Max Act: 0.3685. Min Act: -0.0000

Data Index: 385947 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 0.6070. Min Range: -0.6070

Max Act: 0.3619. Min Act: -0.0000

Data Index: 692454 (C4 (Web Text))

Max Activating Token Index: 305