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

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

Neuron 4365 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.7189. Min Act: -0.0001

Data Index: 1535772 (Python Code)

Max Activating Token Index: 270

Text #1

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.7006. Min Act: -0.0001

Data Index: 839016 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.5341. Min Act: -0.0000

Data Index: 639132 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.5321. Min Act: -0.0000

Data Index: 938253 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.5498. Min Act: -0.0001

Data Index: 51987 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.4855. Min Act: -0.0000

Data Index: 1168056 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.5030. Min Act: -0.0000

Data Index: 994389 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.4311. Min Act: -0.0001

Data Index: 82786 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.4872. Min Act: -0.0000

Data Index: 134617 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.4262. Min Act: -0.0001

Data Index: 356040 (C4 (Web Text))

Max Activating Token Index: 520

Text #10

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.4525. Min Act: -0.0001

Data Index: 329946 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.3911. Min Act: -0.0001

Data Index: 289569 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.3563. Min Act: -0.0001

Data Index: 702569 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.2948. Min Act: -0.0001

Data Index: 501671 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.4538. Min Act: -0.0001

Data Index: 943451 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.2091. Min Act: -0.0000

Data Index: 260750 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.3653. Min Act: -0.0001

Data Index: 1104041 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.2836. Min Act: -0.0001

Data Index: 600892 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.1931. Min Act: -0.0001

Data Index: 746033 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.2249. Min Act: -0.0001

Data Index: 1215581 (C4 (Web Text))

Max Activating Token Index: 161