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

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

Neuron 250 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.3596. Min Act: -0.0000

Data Index: 138443 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.3586. Min Act: -0.0000

Data Index: 435110 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.3025. Min Act: -0.0000

Data Index: 1005946 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.3224. Min Act: -0.0000

Data Index: 512059 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.3006. Min Act: -0.0000

Data Index: 251068 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.3046. Min Act: -0.0000

Data Index: 181172 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.3124. Min Act: -0.0000

Data Index: 563356 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.3079. Min Act: -0.0000

Data Index: 171846 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2964. Min Act: -0.0000

Data Index: 1160144 (C4 (Web Text))

Max Activating Token Index: 170

Text #9

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2765. Min Act: -0.0000

Data Index: 539268 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2959. Min Act: -0.0000

Data Index: 312085 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2862. Min Act: -0.0000

Data Index: 235814 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2900. Min Act: -0.0000

Data Index: 1047625 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2693. Min Act: -0.0000

Data Index: 1091253 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2344. Min Act: -0.0000

Data Index: 313586 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2747. Min Act: -0.0000

Data Index: 1273919 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2916. Min Act: -0.0000

Data Index: 1041100 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2631. Min Act: -0.0000

Data Index: 659230 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2586. Min Act: -0.0000

Data Index: 931907 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2678. Min Act: -0.0000

Data Index: 249972 (C4 (Web Text))

Max Activating Token Index: 190