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

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

Neuron 1181 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: 1.8904. Min Range: -1.8904

Max Act: 1.8904. Min Act: -0.0000

Data Index: 80145 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 1.8904. Min Range: -1.8904

Max Act: 1.7259. Min Act: -0.0000

Data Index: 51285 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 1.8904. Min Range: -1.8904

Max Act: 1.7439. Min Act: -0.0000

Data Index: 1118862 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 1.8904. Min Range: -1.8904

Max Act: 1.6212. Min Act: -0.0000

Data Index: 106022 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 1.8904. Min Range: -1.8904

Max Act: 1.6084. Min Act: -0.0000

Data Index: 31982 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 1.8904. Min Range: -1.8904

Max Act: 1.5923. Min Act: -0.0000

Data Index: 1112451 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 1.8904. Min Range: -1.8904

Max Act: 1.5773. Min Act: -0.0000

Data Index: 93299 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 1.8904. Min Range: -1.8904

Max Act: 1.5341. Min Act: -0.0000

Data Index: 587537 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 1.8904. Min Range: -1.8904

Max Act: 1.5600. Min Act: -0.0000

Data Index: 80267 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 1.8904. Min Range: -1.8904

Max Act: 1.5388. Min Act: -0.0000

Data Index: 657580 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 1.8904. Min Range: -1.8904

Max Act: 1.5291. Min Act: -0.0000

Data Index: 1317574 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 1.8904. Min Range: -1.8904

Max Act: 1.6110. Min Act: -0.0000

Data Index: 34460 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 1.8904. Min Range: -1.8904

Max Act: 1.4180. Min Act: -0.0000

Data Index: 1130320 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 1.8904. Min Range: -1.8904

Max Act: 1.4940. Min Act: -0.0000

Data Index: 88571 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 1.8904. Min Range: -1.8904

Max Act: 1.4793. Min Act: -0.0000

Data Index: 1351784 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 1.8904. Min Range: -1.8904

Max Act: 1.3758. Min Act: -0.0000

Data Index: 1080403 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 1.8904. Min Range: -1.8904

Max Act: 1.4591. Min Act: -0.0000

Data Index: 942735 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 1.8904. Min Range: -1.8904

Max Act: 1.3643. Min Act: -0.0000

Data Index: 765673 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 1.8904. Min Range: -1.8904

Max Act: 1.4327. Min Act: -0.0000

Data Index: 1091059 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 1.8904. Min Range: -1.8904

Max Act: 1.4298. Min Act: -0.0000

Data Index: 284286 (C4 (Web Text))

Max Activating Token Index: 517