Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 872 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3068. Min Range: -1.3068

Max Act: 1.3068. Min Act: -0.0001

Data Index: 67639 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 1.3068. Min Range: -1.3068

Max Act: 1.1256. Min Act: -0.0001

Data Index: 261149 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 1.3068. Min Range: -1.3068

Max Act: 1.1671. Min Act: -0.0001

Data Index: 782588 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 1.3068. Min Range: -1.3068

Max Act: 0.9531. Min Act: -0.0001

Data Index: 192726 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 1.3068. Min Range: -1.3068

Max Act: 0.9809. Min Act: -0.0001

Data Index: 642369 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 1.3068. Min Range: -1.3068

Max Act: 0.9695. Min Act: -0.0001

Data Index: 939409 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 1.3068. Min Range: -1.3068

Max Act: 0.9821. Min Act: -0.0001

Data Index: 994898 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 1.3068. Min Range: -1.3068

Max Act: 0.8241. Min Act: -0.0001

Data Index: 1132407 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 1.3068. Min Range: -1.3068

Max Act: 1.0439. Min Act: -0.0001

Data Index: 907710 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 1.3068. Min Range: -1.3068

Max Act: 0.9569. Min Act: -0.0001

Data Index: 418682 (C4 (Web Text))

Max Activating Token Index: 751

Text #10

Max Range: 1.3068. Min Range: -1.3068

Max Act: 0.9230. Min Act: -0.0001

Data Index: 736779 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 1.3068. Min Range: -1.3068

Max Act: 0.8832. Min Act: -0.0001

Data Index: 790094 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 1.3068. Min Range: -1.3068

Max Act: 0.8022. Min Act: -0.0001

Data Index: 648949 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 1.3068. Min Range: -1.3068

Max Act: 0.8524. Min Act: -0.0001

Data Index: 899803 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 1.3068. Min Range: -1.3068

Max Act: 0.9000. Min Act: -0.0001

Data Index: 927420 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 1.3068. Min Range: -1.3068

Max Act: 0.8056. Min Act: -0.0001

Data Index: 273503 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 1.3068. Min Range: -1.3068

Max Act: 0.8748. Min Act: -0.0001

Data Index: 735366 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 1.3068. Min Range: -1.3068

Max Act: 0.8410. Min Act: -0.0001

Data Index: 885421 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 1.3068. Min Range: -1.3068

Max Act: 0.7481. Min Act: -0.0001

Data Index: 1192706 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 1.3068. Min Range: -1.3068

Max Act: 0.8253. Min Act: -0.0001

Data Index: 512846 (C4 (Web Text))

Max Activating Token Index: 695