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

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

Neuron 2313 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5184. Min Range: -3.5184

Max Act: 3.5184. Min Act: -0.0000

Data Index: 927728 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 3.5184. Min Range: -3.5184

Max Act: 3.3936. Min Act: -0.0000

Data Index: 1147847 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 3.5184. Min Range: -3.5184

Max Act: 3.3727. Min Act: -0.0000

Data Index: 189460 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 3.5184. Min Range: -3.5184

Max Act: 3.3565. Min Act: -0.0000

Data Index: 712940 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 3.5184. Min Range: -3.5184

Max Act: 3.4185. Min Act: -0.0000

Data Index: 56770 (C4 (Web Text))

Max Activating Token Index: 989

Text #5

Max Range: 3.5184. Min Range: -3.5184

Max Act: 3.0747. Min Act: -0.0000

Data Index: 443676 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 3.5184. Min Range: -3.5184

Max Act: 3.1921. Min Act: -0.0000

Data Index: 556258 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 3.5184. Min Range: -3.5184

Max Act: 3.0057. Min Act: -0.0000

Data Index: 138537 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 3.5184. Min Range: -3.5184

Max Act: 3.1093. Min Act: 0.0000

Data Index: 1229372 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 3.5184. Min Range: -3.5184

Max Act: 3.0835. Min Act: -0.0000

Data Index: 1272974 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 3.5184. Min Range: -3.5184

Max Act: 3.0980. Min Act: -0.0000

Data Index: 659170 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 3.5184. Min Range: -3.5184

Max Act: 3.0511. Min Act: -0.0000

Data Index: 1217243 (C4 (Web Text))

Max Activating Token Index: 456

Text #12

Max Range: 3.5184. Min Range: -3.5184

Max Act: 3.0476. Min Act: -0.0000

Data Index: 657908 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 3.5184. Min Range: -3.5184

Max Act: 3.0329. Min Act: -0.0000

Data Index: 299699 (C4 (Web Text))

Max Activating Token Index: 457

Text #14

Max Range: 3.5184. Min Range: -3.5184

Max Act: 3.0256. Min Act: -0.0000

Data Index: 896665 (C4 (Web Text))

Max Activating Token Index: 465

Text #15

Max Range: 3.5184. Min Range: -3.5184

Max Act: 2.9775. Min Act: -0.0000

Data Index: 291801 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 3.5184. Min Range: -3.5184

Max Act: 2.8338. Min Act: -0.0000

Data Index: 872417 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 3.5184. Min Range: -3.5184

Max Act: 2.9675. Min Act: -0.0000

Data Index: 747467 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 3.5184. Min Range: -3.5184

Max Act: 3.1069. Min Act: -0.0000

Data Index: 776504 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 3.5184. Min Range: -3.5184

Max Act: 2.9538. Min Act: -0.0000

Data Index: 197866 (C4 (Web Text))

Max Activating Token Index: 541