Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1352 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.3874. Min Act: -0.0001

Data Index: 1362242 (Python Code)

Max Activating Token Index: 345

Text #1

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.3470. Min Act: -0.0001

Data Index: 1598317 (Python Code)

Max Activating Token Index: 878

Text #2

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.3173. Min Act: -0.0001

Data Index: 1587146 (Python Code)

Max Activating Token Index: 321

Text #3

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.3394. Min Act: -0.0001

Data Index: 1443583 (Python Code)

Max Activating Token Index: 475

Text #4

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.3132. Min Act: -0.0001

Data Index: 1588422 (Python Code)

Max Activating Token Index: 667

Text #5

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.2955. Min Act: -0.0001

Data Index: 1441438 (Python Code)

Max Activating Token Index: 901

Text #6

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.3005. Min Act: -0.0001

Data Index: 1570745 (Python Code)

Max Activating Token Index: 103

Text #7

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.2755. Min Act: -0.0001

Data Index: 1640885 (Python Code)

Max Activating Token Index: 110

Text #8

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.3173. Min Act: -0.0001

Data Index: 1624413 (Python Code)

Max Activating Token Index: 708

Text #9

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.2876. Min Act: -0.0001

Data Index: 1463481 (Python Code)

Max Activating Token Index: 374

Text #10

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.2887. Min Act: -0.0001

Data Index: 1516137 (Python Code)

Max Activating Token Index: 49

Text #11

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.2937. Min Act: -0.0001

Data Index: 1639277 (Python Code)

Max Activating Token Index: 443

Text #12

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.2801. Min Act: -0.0001

Data Index: 1481762 (Python Code)

Max Activating Token Index: 169

Text #13

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.2926. Min Act: -0.0001

Data Index: 1492666 (Python Code)

Max Activating Token Index: 661

Text #14

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.2978. Min Act: -0.0001

Data Index: 1395450 (Python Code)

Max Activating Token Index: 260

Text #15

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.2664. Min Act: -0.0001

Data Index: 1453288 (Python Code)

Max Activating Token Index: 549

Text #16

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.2950. Min Act: -0.0001

Data Index: 1522796 (Python Code)

Max Activating Token Index: 127

Text #17

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.2792. Min Act: -0.0002

Data Index: 1435737 (Python Code)

Max Activating Token Index: 707

Text #18

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.2873. Min Act: -0.0001

Data Index: 1635659 (Python Code)

Max Activating Token Index: 178

Text #19

Max Range: 0.3874. Min Range: -0.3874

Max Act: 0.2857. Min Act: -0.0002

Data Index: 1370824 (Python Code)

Max Activating Token Index: 271