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

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

Neuron 3273 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.2041. Min Act: -0.0000

Data Index: 569115 (C4 (Web Text))

Max Activating Token Index: 482

Text #1

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.2060. Min Act: -0.0000

Data Index: 1223560 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.1861. Min Act: -0.0000

Data Index: 581437 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.1758. Min Act: -0.0000

Data Index: 256274 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.1585. Min Act: -0.0000

Data Index: 475185 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.1518. Min Act: -0.0000

Data Index: 58891 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.1490. Min Act: -0.0000

Data Index: 518252 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.1390. Min Act: -0.0000

Data Index: 415484 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.1439. Min Act: -0.0000

Data Index: 306242 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.1492. Min Act: -0.0000

Data Index: 995758 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.1431. Min Act: -0.0000

Data Index: 53782 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.1406. Min Act: -0.0000

Data Index: 1357075 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.1387. Min Act: -0.0000

Data Index: 666892 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.1358. Min Act: -0.0000

Data Index: 1040431 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.1292. Min Act: -0.0000

Data Index: 1079745 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.1366. Min Act: -0.0000

Data Index: 394132 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.1337. Min Act: -0.0000

Data Index: 733506 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.1255. Min Act: -0.0000

Data Index: 1517284 (Python Code)

Max Activating Token Index: 853

Text #18

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.1412. Min Act: -0.0000

Data Index: 71391 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.1271. Min Act: -0.0000

Data Index: 626704 (C4 (Web Text))

Max Activating Token Index: 734