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

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

Neuron 5247 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: 2.8646. Min Range: -2.8646

Max Act: 2.8646. Min Act: -0.0000

Data Index: 840845 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 2.8646. Min Range: -2.8646

Max Act: 2.4249. Min Act: -0.0000

Data Index: 1056718 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 2.8646. Min Range: -2.8646

Max Act: 2.2111. Min Act: -0.0000

Data Index: 32462 (C4 (Web Text))

Max Activating Token Index: 812

Text #3

Max Range: 2.8646. Min Range: -2.8646

Max Act: 2.1378. Min Act: -0.0000

Data Index: 572397 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 2.8646. Min Range: -2.8646

Max Act: 2.2417. Min Act: -0.0000

Data Index: 1523501 (Python Code)

Max Activating Token Index: 149

Text #5

Max Range: 2.8646. Min Range: -2.8646

Max Act: 2.0736. Min Act: -0.0000

Data Index: 44289 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 2.8646. Min Range: -2.8646

Max Act: 2.0816. Min Act: -0.0000

Data Index: 610815 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 2.8646. Min Range: -2.8646

Max Act: 1.9317. Min Act: -0.0000

Data Index: 898879 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 2.8646. Min Range: -2.8646

Max Act: 1.9771. Min Act: -0.0000

Data Index: 358470 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 2.8646. Min Range: -2.8646

Max Act: 1.8950. Min Act: -0.0000

Data Index: 1314667 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 2.8646. Min Range: -2.8646

Max Act: 1.8425. Min Act: -0.0000

Data Index: 741754 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 2.8646. Min Range: -2.8646

Max Act: 1.8130. Min Act: -0.0000

Data Index: 1086129 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 2.8646. Min Range: -2.8646

Max Act: 1.7878. Min Act: -0.0000

Data Index: 54864 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 2.8646. Min Range: -2.8646

Max Act: 1.7956. Min Act: -0.0000

Data Index: 783069 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 2.8646. Min Range: -2.8646

Max Act: 1.7617. Min Act: -0.0000

Data Index: 1186943 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 2.8646. Min Range: -2.8646

Max Act: 1.7480. Min Act: -0.0000

Data Index: 587774 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 2.8646. Min Range: -2.8646

Max Act: 1.8399. Min Act: -0.0000

Data Index: 718688 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 2.8646. Min Range: -2.8646

Max Act: 1.6259. Min Act: -0.0000

Data Index: 560523 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 2.8646. Min Range: -2.8646

Max Act: 1.7159. Min Act: -0.0000

Data Index: 39821 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 2.8646. Min Range: -2.8646

Max Act: 1.5959. Min Act: -0.0000

Data Index: 1784 (C4 (Web Text))

Max Activating Token Index: 810