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

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

Neuron 4697 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.8887. Min Act: -0.0000

Data Index: 1483020 (Python Code)

Max Activating Token Index: 127

Text #1

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.5750. Min Act: -0.0000

Data Index: 1518839 (Python Code)

Max Activating Token Index: 940

Text #2

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.7835. Min Act: -0.0000

Data Index: 1510218 (Python Code)

Max Activating Token Index: 985

Text #3

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.8142. Min Act: -0.0000

Data Index: 1445350 (Python Code)

Max Activating Token Index: 164

Text #4

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.6647. Min Act: -0.0000

Data Index: 1435659 (Python Code)

Max Activating Token Index: 163

Text #5

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.5199. Min Act: -0.0000

Data Index: 1441560 (Python Code)

Max Activating Token Index: 714

Text #6

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.6878. Min Act: -0.0000

Data Index: 1519724 (Python Code)

Max Activating Token Index: 1002

Text #7

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.6013. Min Act: -0.0001

Data Index: 1591200 (Python Code)

Max Activating Token Index: 208

Text #8

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.6728. Min Act: -0.0001

Data Index: 1388570 (Python Code)

Max Activating Token Index: 429

Text #9

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.5845. Min Act: -0.0001

Data Index: 1564832 (Python Code)

Max Activating Token Index: 142

Text #10

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.6586. Min Act: -0.0001

Data Index: 1576085 (Python Code)

Max Activating Token Index: 902

Text #11

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.5462. Min Act: -0.0000

Data Index: 1569957 (Python Code)

Max Activating Token Index: 916

Text #12

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.4867. Min Act: -0.0000

Data Index: 1619522 (Python Code)

Max Activating Token Index: 165

Text #13

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.5439. Min Act: -0.0001

Data Index: 1535716 (Python Code)

Max Activating Token Index: 831

Text #14

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.5177. Min Act: -0.0000

Data Index: 1463696 (Python Code)

Max Activating Token Index: 695

Text #15

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.4555. Min Act: -0.0000

Data Index: 1535989 (Python Code)

Max Activating Token Index: 720

Text #16

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.4743. Min Act: -0.0000

Data Index: 1652121 (Python Code)

Max Activating Token Index: 213

Text #17

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.4322. Min Act: -0.0000

Data Index: 1482761 (Python Code)

Max Activating Token Index: 553

Text #18

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.3953. Min Act: -0.0001

Data Index: 1394119 (Python Code)

Max Activating Token Index: 707

Text #19

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.3661. Min Act: -0.0001

Data Index: 1605531 (Python Code)

Max Activating Token Index: 161