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

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

Neuron 2446 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.5696. Min Act: -0.0003

Data Index: 762328 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.5355. Min Act: -0.0003

Data Index: 1309933 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.5261. Min Act: -0.0003

Data Index: 1340223 (C4 (Web Text))

Max Activating Token Index: 626

Text #3

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.5217. Min Act: -0.0003

Data Index: 693070 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4860. Min Act: -0.0003

Data Index: 6381 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4926. Min Act: -0.0003

Data Index: 1246351 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4810. Min Act: -0.0003

Data Index: 460108 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4933. Min Act: -0.0003

Data Index: 513342 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4969. Min Act: -0.0003

Data Index: 19322 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4457. Min Act: -0.0003

Data Index: 556594 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4336. Min Act: -0.0003

Data Index: 1124191 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4165. Min Act: -0.0003

Data Index: 605861 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4473. Min Act: -0.0003

Data Index: 72265 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4594. Min Act: -0.0003

Data Index: 225403 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4272. Min Act: -0.0003

Data Index: 881667 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4533. Min Act: -0.0003

Data Index: 940108 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4338. Min Act: -0.0003

Data Index: 171346 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4321. Min Act: -0.0003

Data Index: 1148932 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4477. Min Act: -0.0003

Data Index: 1164667 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4169. Min Act: -0.0003

Data Index: 1108008 (C4 (Web Text))

Max Activating Token Index: 674