Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 818 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3808. Min Range: -0.3808

Max Act: 0.3808. Min Act: -0.0001

Data Index: 227193 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 0.3808. Min Range: -0.3808

Max Act: 0.3761. Min Act: -0.0001

Data Index: 600993 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 0.3808. Min Range: -0.3808

Max Act: 0.3307. Min Act: -0.0001

Data Index: 888229 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 0.3808. Min Range: -0.3808

Max Act: 0.3177. Min Act: -0.0001

Data Index: 162167 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 0.3808. Min Range: -0.3808

Max Act: 0.3375. Min Act: -0.0001

Data Index: 189031 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 0.3808. Min Range: -0.3808

Max Act: 0.3035. Min Act: -0.0001

Data Index: 737265 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 0.3808. Min Range: -0.3808

Max Act: 0.3016. Min Act: -0.0001

Data Index: 1246866 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 0.3808. Min Range: -0.3808

Max Act: 0.3082. Min Act: -0.0001

Data Index: 416527 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 0.3808. Min Range: -0.3808

Max Act: 0.2913. Min Act: -0.0001

Data Index: 1249092 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 0.3808. Min Range: -0.3808

Max Act: 0.2862. Min Act: -0.0001

Data Index: 373238 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 0.3808. Min Range: -0.3808

Max Act: 0.2752. Min Act: -0.0001

Data Index: 21459 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 0.3808. Min Range: -0.3808

Max Act: 0.2587. Min Act: -0.0001

Data Index: 464535 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 0.3808. Min Range: -0.3808

Max Act: 0.2841. Min Act: -0.0001

Data Index: 229555 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 0.3808. Min Range: -0.3808

Max Act: 0.2678. Min Act: -0.0001

Data Index: 459209 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 0.3808. Min Range: -0.3808

Max Act: 0.2752. Min Act: -0.0001

Data Index: 897 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 0.3808. Min Range: -0.3808

Max Act: 0.2749. Min Act: -0.0001

Data Index: 724023 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 0.3808. Min Range: -0.3808

Max Act: 0.2654. Min Act: -0.0001

Data Index: 606290 (C4 (Web Text))

Max Activating Token Index: 656

Text #17

Max Range: 0.3808. Min Range: -0.3808

Max Act: 0.2660. Min Act: -0.0001

Data Index: 191728 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 0.3808. Min Range: -0.3808

Max Act: 0.2489. Min Act: -0.0001

Data Index: 499003 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 0.3808. Min Range: -0.3808

Max Act: 0.2546. Min Act: -0.0001

Data Index: 264365 (C4 (Web Text))

Max Activating Token Index: 295