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

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

Neuron 2210 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.6181. Min Act: -0.0001

Data Index: 177383 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.6930. Min Act: -0.0001

Data Index: 941725 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.6355. Min Act: -0.0001

Data Index: 69119 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.5829. Min Act: -0.0001

Data Index: 73652 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.5991. Min Act: -0.0001

Data Index: 772436 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.6207. Min Act: -0.0001

Data Index: 459262 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.6008. Min Act: -0.0001

Data Index: 845191 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.5721. Min Act: -0.0001

Data Index: 1341312 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.5577. Min Act: -0.0001

Data Index: 1121234 (C4 (Web Text))

Max Activating Token Index: 387

Text #9

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.6066. Min Act: -0.0001

Data Index: 1183244 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.7189. Min Act: -0.0001

Data Index: 1040678 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.5811. Min Act: -0.0001

Data Index: 1370650 (Python Code)

Max Activating Token Index: 399

Text #12

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.6031. Min Act: -0.0001

Data Index: 775410 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.5613. Min Act: -0.0001

Data Index: 1201923 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.6078. Min Act: -0.0001

Data Index: 1136071 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.4982. Min Act: -0.0001

Data Index: 1037392 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.4838. Min Act: -0.0001

Data Index: 647065 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.5513. Min Act: -0.0001

Data Index: 346226 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.3751. Min Act: -0.0001

Data Index: 1110698 (C4 (Web Text))

Max Activating Token Index: 606

Text #19

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.4955. Min Act: -0.0001

Data Index: 1121416 (C4 (Web Text))

Max Activating Token Index: 35