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

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

Neuron 3183 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2020. Min Range: -1.2020

Max Act: 1.2020. Min Act: -0.0000

Data Index: 436603 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 1.2020. Min Range: -1.2020

Max Act: 1.1220. Min Act: -0.0000

Data Index: 268653 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 1.2020. Min Range: -1.2020

Max Act: 1.1432. Min Act: -0.0000

Data Index: 428397 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 1.2020. Min Range: -1.2020

Max Act: 1.1230. Min Act: -0.0000

Data Index: 927222 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 1.2020. Min Range: -1.2020

Max Act: 1.0181. Min Act: -0.0000

Data Index: 460035 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 1.2020. Min Range: -1.2020

Max Act: 1.0724. Min Act: -0.0000

Data Index: 651386 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 1.2020. Min Range: -1.2020

Max Act: 1.0781. Min Act: -0.0000

Data Index: 413973 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 1.2020. Min Range: -1.2020

Max Act: 1.0822. Min Act: -0.0000

Data Index: 1103896 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 1.2020. Min Range: -1.2020

Max Act: 1.0734. Min Act: -0.0000

Data Index: 1251933 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 1.2020. Min Range: -1.2020

Max Act: 1.0071. Min Act: -0.0000

Data Index: 696347 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 1.2020. Min Range: -1.2020

Max Act: 1.0667. Min Act: -0.0000

Data Index: 71888 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 1.2020. Min Range: -1.2020

Max Act: 1.0531. Min Act: -0.0000

Data Index: 266910 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 1.2020. Min Range: -1.2020

Max Act: 1.0506. Min Act: -0.0000

Data Index: 355957 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 1.2020. Min Range: -1.2020

Max Act: 1.0477. Min Act: -0.0000

Data Index: 1010761 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 1.2020. Min Range: -1.2020

Max Act: 0.9806. Min Act: -0.0000

Data Index: 75221 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 1.2020. Min Range: -1.2020

Max Act: 1.0423. Min Act: -0.0000

Data Index: 766273 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 1.2020. Min Range: -1.2020

Max Act: 1.0330. Min Act: -0.0000

Data Index: 1252542 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 1.2020. Min Range: -1.2020

Max Act: 1.0367. Min Act: -0.0000

Data Index: 1200873 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 1.2020. Min Range: -1.2020

Max Act: 1.0396. Min Act: -0.0000

Data Index: 61904 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 1.2020. Min Range: -1.2020

Max Act: 1.0323. Min Act: -0.0000

Data Index: 1082499 (C4 (Web Text))

Max Activating Token Index: 95