Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2004 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.5124. Min Act: -0.0001

Data Index: 842861 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.5964. Min Act: -0.0001

Data Index: 679476 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.5803. Min Act: -0.0001

Data Index: 771780 (C4 (Web Text))

Max Activating Token Index: 364

Text #3

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.5117. Min Act: -0.0001

Data Index: 225152 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.4735. Min Act: -0.0001

Data Index: 580547 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.5068. Min Act: -0.0001

Data Index: 606206 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.4644. Min Act: -0.0001

Data Index: 1277890 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.4441. Min Act: -0.0001

Data Index: 1092021 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.4848. Min Act: -0.0001

Data Index: 777319 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.4925. Min Act: -0.0001

Data Index: 66639 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.4734. Min Act: -0.0001

Data Index: 662744 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.5163. Min Act: -0.0001

Data Index: 184044 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.4893. Min Act: -0.0001

Data Index: 1208493 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.4470. Min Act: -0.0001

Data Index: 150235 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.4650. Min Act: -0.0001

Data Index: 7060 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.4391. Min Act: -0.0001

Data Index: 630843 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.4516. Min Act: -0.0000

Data Index: 550981 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.4466. Min Act: -0.0001

Data Index: 190842 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.4423. Min Act: -0.0001

Data Index: 650755 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.4451. Min Act: -0.0001

Data Index: 1132425 (C4 (Web Text))

Max Activating Token Index: 334