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

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

Neuron 4774 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0136. Min Act: -0.0002

Data Index: 1161880 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0132. Min Act: -0.0002

Data Index: 1261559 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0109. Min Act: -0.0002

Data Index: 649616 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0107. Min Act: -0.0002

Data Index: 526299 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0103. Min Act: -0.0002

Data Index: 168593 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0103. Min Act: -0.0002

Data Index: 365902 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0101. Min Act: -0.0002

Data Index: 293531 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0097. Min Act: -0.0002

Data Index: 289586 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0097. Min Act: -0.0002

Data Index: 724667 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0094. Min Act: -0.0002

Data Index: 1323870 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0095. Min Act: -0.0002

Data Index: 885680 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0095. Min Act: -0.0002

Data Index: 924212 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0094. Min Act: -0.0002

Data Index: 368958 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0093. Min Act: -0.0002

Data Index: 349290 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0093. Min Act: -0.0002

Data Index: 806285 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0093. Min Act: -0.0002

Data Index: 231931 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0092. Min Act: -0.0002

Data Index: 1169623 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0092. Min Act: -0.0002

Data Index: 852148 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0092. Min Act: -0.0002

Data Index: 332271 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0092. Min Act: -0.0002

Data Index: 1006791 (C4 (Web Text))

Max Activating Token Index: 769