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

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

Neuron 4140 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: 0.7258. Min Range: -0.7258

Max Act: 0.7258. Min Act: -0.0002

Data Index: 384842 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.7258. Min Act: -0.0002

Data Index: 273819 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.7258. Min Act: -0.0002

Data Index: 986597 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.6644. Min Act: -0.0002

Data Index: 863685 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.6261. Min Act: -0.0002

Data Index: 136188 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.6229. Min Act: -0.0002

Data Index: 93844 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.6113. Min Act: -0.0002

Data Index: 155214 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.5970. Min Act: -0.0003

Data Index: 744450 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.5920. Min Act: -0.0003

Data Index: 645125 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.6082. Min Act: -0.0002

Data Index: 1040110 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.6028. Min Act: -0.0002

Data Index: 1099190 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.5968. Min Act: -0.0002

Data Index: 297762 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.5909. Min Act: -0.0002

Data Index: 453703 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.5777. Min Act: -0.0002

Data Index: 1337715 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.5866. Min Act: -0.0002

Data Index: 937592 (C4 (Web Text))

Max Activating Token Index: 403

Text #15

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.5885. Min Act: -0.0002

Data Index: 529796 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.5667. Min Act: -0.0002

Data Index: 393170 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.5637. Min Act: -0.0002

Data Index: 21137 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.5711. Min Act: -0.0002

Data Index: 934972 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.5762. Min Act: -0.0002

Data Index: 231577 (C4 (Web Text))

Max Activating Token Index: 226