Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1420 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.5035. Min Act: -0.0001

Data Index: 502976 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.4728. Min Act: -0.0001

Data Index: 991764 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.4340. Min Act: -0.0001

Data Index: 866424 (C4 (Web Text))

Max Activating Token Index: 276

Text #3

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.4668. Min Act: -0.0001

Data Index: 818416 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.4489. Min Act: -0.0001

Data Index: 47273 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.4510. Min Act: -0.0001

Data Index: 823162 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.3984. Min Act: -0.0001

Data Index: 1209319 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.4200. Min Act: -0.0001

Data Index: 109987 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.4758. Min Act: -0.0001

Data Index: 1183156 (C4 (Web Text))

Max Activating Token Index: 868

Text #9

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.3614. Min Act: -0.0001

Data Index: 627442 (C4 (Web Text))

Max Activating Token Index: 708

Text #10

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.3796. Min Act: -0.0001

Data Index: 74746 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.4054. Min Act: -0.0001

Data Index: 626073 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.4010. Min Act: -0.0001

Data Index: 410009 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.3811. Min Act: -0.0001

Data Index: 136343 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.3910. Min Act: -0.0001

Data Index: 208652 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.3902. Min Act: -0.0001

Data Index: 734838 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.3790. Min Act: -0.0001

Data Index: 326525 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.3843. Min Act: -0.0001

Data Index: 757278 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.4107. Min Act: -0.0001

Data Index: 1237943 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.3782. Min Act: -0.0001

Data Index: 301220 (C4 (Web Text))

Max Activating Token Index: 174