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

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

Neuron 5019 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0155. Min Range: -1.0155

Max Act: 1.0155. Min Act: -0.0001

Data Index: 354658 (C4 (Web Text))

Max Activating Token Index: 952

Text #1

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.8986. Min Act: -0.0001

Data Index: 934683 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.8338. Min Act: -0.0001

Data Index: 636848 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.7721. Min Act: -0.0001

Data Index: 937586 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.8141. Min Act: -0.0001

Data Index: 643492 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.7121. Min Act: -0.0001

Data Index: 490837 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.7131. Min Act: -0.0001

Data Index: 397378 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.6726. Min Act: -0.0001

Data Index: 666766 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.6460. Min Act: -0.0001

Data Index: 762145 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.5808. Min Act: -0.0001

Data Index: 82684 (C4 (Web Text))

Max Activating Token Index: 768

Text #10

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.5316. Min Act: -0.0001

Data Index: 121890 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.6050. Min Act: -0.0001

Data Index: 39652 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.5532. Min Act: -0.0001

Data Index: 979460 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.6051. Min Act: -0.0001

Data Index: 52832 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.5862. Min Act: -0.0001

Data Index: 369160 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.6032. Min Act: -0.0001

Data Index: 963552 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.5848. Min Act: -0.0001

Data Index: 104239 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.6086. Min Act: -0.0001

Data Index: 135744 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.5484. Min Act: -0.0001

Data Index: 308009 (C4 (Web Text))

Max Activating Token Index: 713

Text #19

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.5798. Min Act: -0.0001

Data Index: 783381 (C4 (Web Text))

Max Activating Token Index: 427