Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3028 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9249. Min Range: -0.9249

Max Act: 0.9249. Min Act: -0.0001

Data Index: 215409 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 0.9249. Min Range: -0.9249

Max Act: 0.9184. Min Act: -0.0001

Data Index: 369369 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 0.9249. Min Range: -0.9249

Max Act: 0.9086. Min Act: -0.0001

Data Index: 1320527 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.9249. Min Range: -0.9249

Max Act: 0.9141. Min Act: -0.0002

Data Index: 1177381 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 0.9249. Min Range: -0.9249

Max Act: 0.8773. Min Act: -0.0001

Data Index: 152986 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 0.9249. Min Range: -0.9249

Max Act: 0.8514. Min Act: -0.0001

Data Index: 1133976 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 0.9249. Min Range: -0.9249

Max Act: 0.8307. Min Act: -0.0001

Data Index: 100933 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 0.9249. Min Range: -0.9249

Max Act: 0.8037. Min Act: -0.0001

Data Index: 1174630 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 0.9249. Min Range: -0.9249

Max Act: 0.7859. Min Act: -0.0002

Data Index: 610365 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 0.9249. Min Range: -0.9249

Max Act: 0.7989. Min Act: -0.0001

Data Index: 427727 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 0.9249. Min Range: -0.9249

Max Act: 0.8233. Min Act: -0.0001

Data Index: 1266470 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 0.9249. Min Range: -0.9249

Max Act: 0.8410. Min Act: -0.0002

Data Index: 877390 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 0.9249. Min Range: -0.9249

Max Act: 0.8107. Min Act: -0.0001

Data Index: 506108 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 0.9249. Min Range: -0.9249

Max Act: 0.7837. Min Act: -0.0001

Data Index: 744707 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.9249. Min Range: -0.9249

Max Act: 0.8015. Min Act: -0.0001

Data Index: 393820 (C4 (Web Text))

Max Activating Token Index: 947

Text #15

Max Range: 0.9249. Min Range: -0.9249

Max Act: 0.7761. Min Act: -0.0001

Data Index: 26936 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 0.9249. Min Range: -0.9249

Max Act: 0.7483. Min Act: -0.0002

Data Index: 1290813 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 0.9249. Min Range: -0.9249

Max Act: 0.6967. Min Act: -0.0001

Data Index: 937410 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 0.9249. Min Range: -0.9249

Max Act: 0.7622. Min Act: -0.0001

Data Index: 1257873 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 0.9249. Min Range: -0.9249

Max Act: 0.7577. Min Act: -0.0001

Data Index: 376104 (C4 (Web Text))

Max Activating Token Index: 20