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

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

Neuron 2647 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2181. Min Range: -1.2181

Max Act: 1.2181. Min Act: -0.0000

Data Index: 559836 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 1.2181. Min Range: -1.2181

Max Act: 1.1814. Min Act: -0.0000

Data Index: 846241 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 1.2181. Min Range: -1.2181

Max Act: 1.0470. Min Act: -0.0000

Data Index: 243209 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 1.2181. Min Range: -1.2181

Max Act: 1.0172. Min Act: -0.0000

Data Index: 922718 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 1.2181. Min Range: -1.2181

Max Act: 1.1551. Min Act: -0.0000

Data Index: 1506348 (Python Code)

Max Activating Token Index: 946

Text #5

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.9633. Min Act: -0.0000

Data Index: 1588954 (Python Code)

Max Activating Token Index: 815

Text #6

Max Range: 1.2181. Min Range: -1.2181

Max Act: 1.0316. Min Act: -0.0000

Data Index: 417897 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.9740. Min Act: -0.0000

Data Index: 559975 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.9183. Min Act: -0.0000

Data Index: 1522939 (Python Code)

Max Activating Token Index: 862

Text #9

Max Range: 1.2181. Min Range: -1.2181

Max Act: 1.0083. Min Act: -0.0000

Data Index: 728781 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.9682. Min Act: -0.0000

Data Index: 1434147 (Python Code)

Max Activating Token Index: 202

Text #11

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.9687. Min Act: -0.0000

Data Index: 1291379 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.9309. Min Act: -0.0000

Data Index: 1419559 (Python Code)

Max Activating Token Index: 211

Text #13

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.9477. Min Act: -0.0000

Data Index: 1181770 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.8820. Min Act: -0.0000

Data Index: 1366352 (Python Code)

Max Activating Token Index: 414

Text #15

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.9272. Min Act: -0.0000

Data Index: 1396665 (Python Code)

Max Activating Token Index: 245

Text #16

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.9323. Min Act: -0.0000

Data Index: 36740 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.8988. Min Act: -0.0000

Data Index: 334292 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.8729. Min Act: -0.0000

Data Index: 1274689 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.8889. Min Act: -0.0000

Data Index: 510227 (C4 (Web Text))

Max Activating Token Index: 735