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

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

Neuron 3085 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1064. Min Range: -2.1064

Max Act: 2.1064. Min Act: -0.0000

Data Index: 208655 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 2.1064. Min Range: -2.1064

Max Act: 1.8211. Min Act: -0.0000

Data Index: 949049 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 2.1064. Min Range: -2.1064

Max Act: 1.6688. Min Act: -0.0000

Data Index: 197512 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 2.1064. Min Range: -2.1064

Max Act: 1.6425. Min Act: -0.0000

Data Index: 121542 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 2.1064. Min Range: -2.1064

Max Act: 1.5967. Min Act: -0.0000

Data Index: 1169485 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 2.1064. Min Range: -2.1064

Max Act: 1.6835. Min Act: -0.0000

Data Index: 1305921 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 2.1064. Min Range: -2.1064

Max Act: 1.6767. Min Act: -0.0000

Data Index: 887431 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 2.1064. Min Range: -2.1064

Max Act: 1.5448. Min Act: -0.0000

Data Index: 38771 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 2.1064. Min Range: -2.1064

Max Act: 1.5191. Min Act: -0.0000

Data Index: 596773 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 2.1064. Min Range: -2.1064

Max Act: 1.5105. Min Act: -0.0000

Data Index: 323086 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 2.1064. Min Range: -2.1064

Max Act: 1.6014. Min Act: -0.0000

Data Index: 853005 (C4 (Web Text))

Max Activating Token Index: 195

Text #11

Max Range: 2.1064. Min Range: -2.1064

Max Act: 1.5809. Min Act: -0.0000

Data Index: 121064 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 2.1064. Min Range: -2.1064

Max Act: 1.5724. Min Act: -0.0000

Data Index: 866729 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 2.1064. Min Range: -2.1064

Max Act: 1.4853. Min Act: -0.0000

Data Index: 787834 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 2.1064. Min Range: -2.1064

Max Act: 1.5563. Min Act: -0.0000

Data Index: 375936 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 2.1064. Min Range: -2.1064

Max Act: 1.5677. Min Act: -0.0000

Data Index: 1181187 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 2.1064. Min Range: -2.1064

Max Act: 1.5237. Min Act: -0.0000

Data Index: 360074 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 2.1064. Min Range: -2.1064

Max Act: 1.5287. Min Act: -0.0000

Data Index: 1073788 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 2.1064. Min Range: -2.1064

Max Act: 1.4676. Min Act: -0.0000

Data Index: 644563 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 2.1064. Min Range: -2.1064

Max Act: 1.5546. Min Act: -0.0000

Data Index: 441279 (C4 (Web Text))

Max Activating Token Index: 281