Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5436 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.9463. Min Act: -0.0000

Data Index: 653739 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.8166. Min Act: -0.0000

Data Index: 918746 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.8086. Min Act: -0.0000

Data Index: 420751 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.8488. Min Act: -0.0000

Data Index: 1022033 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.8125. Min Act: -0.0000

Data Index: 1212340 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.7764. Min Act: -0.0000

Data Index: 1240999 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.7310. Min Act: -0.0000

Data Index: 821911 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.7211. Min Act: -0.0000

Data Index: 668084 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.6975. Min Act: -0.0000

Data Index: 738927 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.7271. Min Act: -0.0000

Data Index: 1213733 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.5585. Min Act: -0.0000

Data Index: 347928 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.5691. Min Act: -0.0000

Data Index: 1317279 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.5474. Min Act: -0.0000

Data Index: 1186432 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.5257. Min Act: -0.0000

Data Index: 224936 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.5758. Min Act: -0.0000

Data Index: 1216497 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.5393. Min Act: -0.0000

Data Index: 763995 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.5380. Min Act: -0.0000

Data Index: 950363 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.5507. Min Act: -0.0000

Data Index: 576197 (C4 (Web Text))

Max Activating Token Index: 415

Text #18

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.5283. Min Act: -0.0000

Data Index: 354418 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.5489. Min Act: -0.0000

Data Index: 136131 (C4 (Web Text))

Max Activating Token Index: 831