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

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

Neuron 1848 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3034. Min Range: -2.3034

Max Act: 2.3034. Min Act: -0.0000

Data Index: 1351612 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 2.3034. Min Range: -2.3034

Max Act: 2.2125. Min Act: -0.0000

Data Index: 365714 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 2.3034. Min Range: -2.3034

Max Act: 2.1647. Min Act: -0.0000

Data Index: 136673 (C4 (Web Text))

Max Activating Token Index: 602

Text #3

Max Range: 2.3034. Min Range: -2.3034

Max Act: 1.8910. Min Act: -0.0000

Data Index: 1074085 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 2.3034. Min Range: -2.3034

Max Act: 2.0439. Min Act: -0.0000

Data Index: 864351 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 2.3034. Min Range: -2.3034

Max Act: 1.9067. Min Act: -0.0000

Data Index: 304180 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 2.3034. Min Range: -2.3034

Max Act: 1.8580. Min Act: -0.0000

Data Index: 773671 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 2.3034. Min Range: -2.3034

Max Act: 1.8485. Min Act: -0.0000

Data Index: 1198678 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 2.3034. Min Range: -2.3034

Max Act: 1.7166. Min Act: -0.0000

Data Index: 1152099 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 2.3034. Min Range: -2.3034

Max Act: 1.7502. Min Act: -0.0000

Data Index: 846887 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 2.3034. Min Range: -2.3034

Max Act: 1.7335. Min Act: -0.0000

Data Index: 1005196 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 2.3034. Min Range: -2.3034

Max Act: 1.7159. Min Act: -0.0000

Data Index: 891217 (C4 (Web Text))

Max Activating Token Index: 756

Text #12

Max Range: 2.3034. Min Range: -2.3034

Max Act: 1.7208. Min Act: -0.0000

Data Index: 175589 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 2.3034. Min Range: -2.3034

Max Act: 1.7190. Min Act: -0.0000

Data Index: 66827 (C4 (Web Text))

Max Activating Token Index: 424

Text #14

Max Range: 2.3034. Min Range: -2.3034

Max Act: 1.7092. Min Act: -0.0000

Data Index: 194026 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 2.3034. Min Range: -2.3034

Max Act: 1.7002. Min Act: -0.0000

Data Index: 809504 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 2.3034. Min Range: -2.3034

Max Act: 1.6987. Min Act: -0.0000

Data Index: 1233366 (C4 (Web Text))

Max Activating Token Index: 378

Text #17

Max Range: 2.3034. Min Range: -2.3034

Max Act: 1.6976. Min Act: -0.0000

Data Index: 878351 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 2.3034. Min Range: -2.3034

Max Act: 1.6943. Min Act: -0.0000

Data Index: 26255 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 2.3034. Min Range: -2.3034

Max Act: 1.6820. Min Act: -0.0000

Data Index: 1117783 (C4 (Web Text))

Max Activating Token Index: 734