Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1935 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1180. Min Act: -0.0005

Data Index: 4674 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1051. Min Act: -0.0005

Data Index: 1185237 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1115. Min Act: -0.0005

Data Index: 163527 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0986. Min Act: -0.0005

Data Index: 399035 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1035. Min Act: -0.0005

Data Index: 385199 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1030. Min Act: -0.0005

Data Index: 637048 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1025. Min Act: -0.0005

Data Index: 392064 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0986. Min Act: -0.0005

Data Index: 1178704 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0967. Min Act: -0.0004

Data Index: 245892 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0983. Min Act: -0.0005

Data Index: 1158662 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0950. Min Act: -0.0005

Data Index: 1037571 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0951. Min Act: -0.0004

Data Index: 420435 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0969. Min Act: -0.0005

Data Index: 437922 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0906. Min Act: -0.0005

Data Index: 48779 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1042. Min Act: -0.0005

Data Index: 1246411 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0939. Min Act: -0.0005

Data Index: 939787 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0953. Min Act: -0.0005

Data Index: 1066120 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0919. Min Act: -0.0005

Data Index: 678403 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0897. Min Act: -0.0005

Data Index: 665117 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1001. Min Act: -0.0005

Data Index: 1081670 (C4 (Web Text))

Max Activating Token Index: 94