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

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

Neuron 2048 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: 0.1322. Min Range: -0.1322

Max Act: 0.1322. Min Act: -0.0002

Data Index: 328003 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1146. Min Act: -0.0002

Data Index: 1001380 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1104. Min Act: -0.0002

Data Index: 225331 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1049. Min Act: -0.0002

Data Index: 580113 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1107. Min Act: -0.0002

Data Index: 486198 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1102. Min Act: -0.0002

Data Index: 464712 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1049. Min Act: -0.0001

Data Index: 280436 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1007. Min Act: -0.0002

Data Index: 192624 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1066. Min Act: -0.0002

Data Index: 145309 (C4 (Web Text))

Max Activating Token Index: 170

Text #9

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1019. Min Act: -0.0002

Data Index: 358596 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0974. Min Act: -0.0002

Data Index: 571810 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1008. Min Act: -0.0002

Data Index: 1113559 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1000. Min Act: -0.0002

Data Index: 330391 (C4 (Web Text))

Max Activating Token Index: 873

Text #13

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0946. Min Act: -0.0002

Data Index: 927018 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1017. Min Act: -0.0002

Data Index: 170161 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0997. Min Act: -0.0002

Data Index: 1088070 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1047. Min Act: -0.0002

Data Index: 138620 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0964. Min Act: -0.0002

Data Index: 1345343 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0933. Min Act: -0.0002

Data Index: 314529 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0965. Min Act: -0.0002

Data Index: 27449 (C4 (Web Text))

Max Activating Token Index: 244