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

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

Neuron 3482 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.9002. Min Act: -0.0000

Data Index: 887723 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.8838. Min Act: -0.0000

Data Index: 59902 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.8091. Min Act: -0.0000

Data Index: 1012814 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.7829. Min Act: -0.0000

Data Index: 429995 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.7404. Min Act: -0.0000

Data Index: 1249157 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.7578. Min Act: -0.0000

Data Index: 250151 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.7192. Min Act: -0.0000

Data Index: 1558162 (Python Code)

Max Activating Token Index: 122

Text #7

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.7016. Min Act: -0.0000

Data Index: 1128691 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.6932. Min Act: -0.0000

Data Index: 1330581 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.7059. Min Act: -0.0000

Data Index: 559583 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.6650. Min Act: -0.0000

Data Index: 320331 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.6560. Min Act: -0.0000

Data Index: 683764 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.6320. Min Act: -0.0000

Data Index: 896690 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.6647. Min Act: -0.0000

Data Index: 537275 (C4 (Web Text))

Max Activating Token Index: 668

Text #14

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.6287. Min Act: -0.0000

Data Index: 254997 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.6286. Min Act: -0.0000

Data Index: 1043607 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.6111. Min Act: -0.0000

Data Index: 241 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.6097. Min Act: -0.0000

Data Index: 1134599 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.5727. Min Act: -0.0000

Data Index: 877736 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.5803. Min Act: -0.0000

Data Index: 892692 (C4 (Web Text))

Max Activating Token Index: 272