Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1493 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1341. Min Act: -0.0000

Data Index: 6946 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1233. Min Act: -0.0000

Data Index: 1143662 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1071. Min Act: -0.0000

Data Index: 964127 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1064. Min Act: -0.0000

Data Index: 575052 (C4 (Web Text))

Max Activating Token Index: 731

Text #4

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.0946. Min Act: -0.0000

Data Index: 1051519 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.0968. Min Act: -0.0000

Data Index: 308121 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1046. Min Act: -0.0000

Data Index: 544050 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.0953. Min Act: -0.0000

Data Index: 565581 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.0865. Min Act: -0.0000

Data Index: 841494 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.0894. Min Act: -0.0000

Data Index: 1160833 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.0875. Min Act: -0.0000

Data Index: 1236161 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.0834. Min Act: -0.0000

Data Index: 193934 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.0875. Min Act: -0.0000

Data Index: 1240537 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.0834. Min Act: -0.0000

Data Index: 591119 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.0843. Min Act: -0.0000

Data Index: 1324766 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.0851. Min Act: -0.0000

Data Index: 849797 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.0829. Min Act: -0.0000

Data Index: 1387117 (Python Code)

Max Activating Token Index: 897

Text #17

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.0829. Min Act: -0.0000

Data Index: 258988 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.0806. Min Act: -0.0000

Data Index: 162861 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.0810. Min Act: -0.0000

Data Index: 696474 (C4 (Web Text))

Max Activating Token Index: 517