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

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

Neuron 5280 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: 3.6107. Min Range: -3.6107

Max Act: 3.6104. Min Act: -0.0000

Data Index: 382398 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 3.6107. Min Range: -3.6107

Max Act: 3.4290. Min Act: -0.0000

Data Index: 1163106 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 3.6107. Min Range: -3.6107

Max Act: 3.3410. Min Act: -0.0000

Data Index: 1022892 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 3.6107. Min Range: -3.6107

Max Act: 3.4976. Min Act: -0.0000

Data Index: 1185435 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 3.6107. Min Range: -3.6107

Max Act: 3.3342. Min Act: -0.0000

Data Index: 930411 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 3.6107. Min Range: -3.6107

Max Act: 3.3203. Min Act: -0.0000

Data Index: 64629 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 3.6107. Min Range: -3.6107

Max Act: 3.3019. Min Act: -0.0000

Data Index: 1201025 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 3.6107. Min Range: -3.6107

Max Act: 3.2691. Min Act: -0.0000

Data Index: 1650486 (Python Code)

Max Activating Token Index: 136

Text #8

Max Range: 3.6107. Min Range: -3.6107

Max Act: 3.4168. Min Act: -0.0000

Data Index: 514963 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 3.6107. Min Range: -3.6107

Max Act: 3.1833. Min Act: -0.0000

Data Index: 751239 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 3.6107. Min Range: -3.6107

Max Act: 3.3377. Min Act: -0.0000

Data Index: 1341624 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 3.6107. Min Range: -3.6107

Max Act: 3.1887. Min Act: -0.0000

Data Index: 293950 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 3.6107. Min Range: -3.6107

Max Act: 3.3275. Min Act: -0.0000

Data Index: 1274118 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 3.6107. Min Range: -3.6107

Max Act: 3.3302. Min Act: -0.0000

Data Index: 917542 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 3.6107. Min Range: -3.6107

Max Act: 3.3152. Min Act: -0.0000

Data Index: 1007000 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 3.6107. Min Range: -3.6107

Max Act: 3.6107. Min Act: -0.0000

Data Index: 990342 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 3.6107. Min Range: -3.6107

Max Act: 3.3053. Min Act: -0.0000

Data Index: 1292730 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 3.6107. Min Range: -3.6107

Max Act: 3.1697. Min Act: -0.0000

Data Index: 725453 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 3.6107. Min Range: -3.6107

Max Act: 3.0269. Min Act: -0.0000

Data Index: 1035576 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 3.6107. Min Range: -3.6107

Max Act: 3.2965. Min Act: -0.0000

Data Index: 1369109 (Python Code)

Max Activating Token Index: 111