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

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

Neuron 607 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: 2.0787. Min Range: -2.0787

Max Act: 2.0787. Min Act: -0.0000

Data Index: 964013 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 2.0787. Min Range: -2.0787

Max Act: 1.7986. Min Act: -0.0000

Data Index: 491831 (C4 (Web Text))

Max Activating Token Index: 714

Text #2

Max Range: 2.0787. Min Range: -2.0787

Max Act: 1.8196. Min Act: -0.0000

Data Index: 1132284 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 2.0787. Min Range: -2.0787

Max Act: 1.5166. Min Act: -0.0000

Data Index: 1062316 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 2.0787. Min Range: -2.0787

Max Act: 1.7080. Min Act: -0.0000

Data Index: 203069 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 2.0787. Min Range: -2.0787

Max Act: 1.6279. Min Act: -0.0000

Data Index: 1065549 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 2.0787. Min Range: -2.0787

Max Act: 1.5591. Min Act: -0.0000

Data Index: 1327004 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 2.0787. Min Range: -2.0787

Max Act: 1.5161. Min Act: -0.0000

Data Index: 491970 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 2.0787. Min Range: -2.0787

Max Act: 1.3182. Min Act: -0.0000

Data Index: 154916 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 2.0787. Min Range: -2.0787

Max Act: 1.4093. Min Act: -0.0000

Data Index: 1267929 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 2.0787. Min Range: -2.0787

Max Act: 1.4038. Min Act: -0.0000

Data Index: 221217 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 2.0787. Min Range: -2.0787

Max Act: 1.5027. Min Act: -0.0000

Data Index: 251166 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 2.0787. Min Range: -2.0787

Max Act: 1.3703. Min Act: -0.0000

Data Index: 1096876 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 2.0787. Min Range: -2.0787

Max Act: 1.3287. Min Act: -0.0000

Data Index: 446124 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 2.0787. Min Range: -2.0787

Max Act: 1.6145. Min Act: -0.0000

Data Index: 359781 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 2.0787. Min Range: -2.0787

Max Act: 1.3694. Min Act: -0.0000

Data Index: 338119 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 2.0787. Min Range: -2.0787

Max Act: 1.1990. Min Act: -0.0000

Data Index: 1154890 (C4 (Web Text))

Max Activating Token Index: 641

Text #17

Max Range: 2.0787. Min Range: -2.0787

Max Act: 1.3582. Min Act: -0.0000

Data Index: 1076153 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 2.0787. Min Range: -2.0787

Max Act: 1.3843. Min Act: -0.0000

Data Index: 475853 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 2.0787. Min Range: -2.0787

Max Act: 1.3688. Min Act: -0.0000

Data Index: 551301 (C4 (Web Text))

Max Activating Token Index: 181