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

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

Neuron 2418 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5201. Min Range: -1.5201

Max Act: 1.5201. Min Act: -0.0000

Data Index: 1289623 (C4 (Web Text))

Max Activating Token Index: 165

Text #1

Max Range: 1.5201. Min Range: -1.5201

Max Act: 1.2934. Min Act: -0.0000

Data Index: 825886 (C4 (Web Text))

Max Activating Token Index: 420

Text #2

Max Range: 1.5201. Min Range: -1.5201

Max Act: 1.3195. Min Act: -0.0000

Data Index: 251608 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 1.5201. Min Range: -1.5201

Max Act: 1.2308. Min Act: -0.0001

Data Index: 21091 (C4 (Web Text))

Max Activating Token Index: 476

Text #4

Max Range: 1.5201. Min Range: -1.5201

Max Act: 1.2411. Min Act: -0.0000

Data Index: 1252957 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 1.5201. Min Range: -1.5201

Max Act: 1.0660. Min Act: -0.0001

Data Index: 820035 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 1.5201. Min Range: -1.5201

Max Act: 1.1783. Min Act: -0.0000

Data Index: 236428 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 1.5201. Min Range: -1.5201

Max Act: 1.0788. Min Act: -0.0000

Data Index: 395843 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 1.5201. Min Range: -1.5201

Max Act: 1.0586. Min Act: -0.0000

Data Index: 107314 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 1.5201. Min Range: -1.5201

Max Act: 0.9716. Min Act: -0.0001

Data Index: 204472 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 1.5201. Min Range: -1.5201

Max Act: 1.0489. Min Act: -0.0000

Data Index: 31421 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 1.5201. Min Range: -1.5201

Max Act: 1.0988. Min Act: -0.0001

Data Index: 881587 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 1.5201. Min Range: -1.5201

Max Act: 1.0548. Min Act: -0.0000

Data Index: 691220 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 1.5201. Min Range: -1.5201

Max Act: 1.0011. Min Act: -0.0000

Data Index: 969847 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 1.5201. Min Range: -1.5201

Max Act: 0.8666. Min Act: -0.0000

Data Index: 823981 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 1.5201. Min Range: -1.5201

Max Act: 0.9282. Min Act: -0.0001

Data Index: 772447 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 1.5201. Min Range: -1.5201

Max Act: 0.9258. Min Act: -0.0001

Data Index: 1271216 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 1.5201. Min Range: -1.5201

Max Act: 0.9164. Min Act: -0.0000

Data Index: 945470 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 1.5201. Min Range: -1.5201

Max Act: 0.8856. Min Act: -0.0000

Data Index: 409328 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 1.5201. Min Range: -1.5201

Max Act: 0.9372. Min Act: -0.0000

Data Index: 360959 (C4 (Web Text))

Max Activating Token Index: 170