Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4732 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 2.1148. Min Range: -2.1148

Max Act: 2.1148. Min Act: -0.0002

Data Index: 557344 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 2.1148. Min Range: -2.1148

Max Act: 1.9108. Min Act: -0.0002

Data Index: 880832 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 2.1148. Min Range: -2.1148

Max Act: 1.8794. Min Act: -0.0002

Data Index: 1259182 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 2.1148. Min Range: -2.1148

Max Act: 1.7472. Min Act: -0.0002

Data Index: 1272332 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 2.1148. Min Range: -2.1148

Max Act: 1.7477. Min Act: -0.0002

Data Index: 984566 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 2.1148. Min Range: -2.1148

Max Act: 1.6724. Min Act: -0.0002

Data Index: 566943 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 2.1148. Min Range: -2.1148

Max Act: 1.6631. Min Act: -0.0002

Data Index: 1019281 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 2.1148. Min Range: -2.1148

Max Act: 1.6401. Min Act: -0.0002

Data Index: 861826 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 2.1148. Min Range: -2.1148

Max Act: 1.6592. Min Act: -0.0002

Data Index: 568858 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 2.1148. Min Range: -2.1148

Max Act: 1.5677. Min Act: -0.0002

Data Index: 1347561 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 2.1148. Min Range: -2.1148

Max Act: 1.6515. Min Act: -0.0002

Data Index: 618862 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 2.1148. Min Range: -2.1148

Max Act: 1.6661. Min Act: -0.0002

Data Index: 904612 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 2.1148. Min Range: -2.1148

Max Act: 1.5792. Min Act: -0.0002

Data Index: 503359 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 2.1148. Min Range: -2.1148

Max Act: 1.6854. Min Act: -0.0002

Data Index: 47768 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 2.1148. Min Range: -2.1148

Max Act: 1.5655. Min Act: -0.0002

Data Index: 930515 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 2.1148. Min Range: -2.1148

Max Act: 1.6081. Min Act: -0.0002

Data Index: 82517 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 2.1148. Min Range: -2.1148

Max Act: 1.5786. Min Act: -0.0002

Data Index: 745948 (C4 (Web Text))

Max Activating Token Index: 249

Text #17

Max Range: 2.1148. Min Range: -2.1148

Max Act: 1.6097. Min Act: -0.0002

Data Index: 836516 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 2.1148. Min Range: -2.1148

Max Act: 1.6054. Min Act: -0.0002

Data Index: 340865 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 2.1148. Min Range: -2.1148

Max Act: 1.5048. Min Act: -0.0002

Data Index: 38771 (C4 (Web Text))

Max Activating Token Index: 177