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

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

Neuron 2307 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: 0.0102. Min Range: -0.0102

Max Act: 0.0102. Min Act: -0.0002

Data Index: 961274 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0096. Min Act: -0.0002

Data Index: 190380 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0090. Min Act: -0.0002

Data Index: 1176327 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0091. Min Act: -0.0002

Data Index: 995607 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0089. Min Act: -0.0002

Data Index: 590735 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0088. Min Act: -0.0002

Data Index: 1313574 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0087. Min Act: -0.0002

Data Index: 395392 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0086. Min Act: -0.0002

Data Index: 324287 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0084. Min Act: -0.0002

Data Index: 298000 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0084. Min Act: -0.0002

Data Index: 400196 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0083. Min Act: -0.0002

Data Index: 849474 (C4 (Web Text))

Max Activating Token Index: 797

Text #11

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0083. Min Act: -0.0002

Data Index: 339490 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0083. Min Act: -0.0002

Data Index: 40310 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0083. Min Act: -0.0002

Data Index: 512567 (C4 (Web Text))

Max Activating Token Index: 259

Text #14

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0082. Min Act: -0.0002

Data Index: 596678 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0082. Min Act: -0.0002

Data Index: 1355776 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0081. Min Act: -0.0002

Data Index: 805835 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0083. Min Act: -0.0002

Data Index: 27705 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0081. Min Act: -0.0002

Data Index: 209500 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0081. Min Act: -0.0002

Data Index: 826360 (C4 (Web Text))

Max Activating Token Index: 304