Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 312 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4197. Min Range: -1.4197

Max Act: 1.4197. Min Act: -0.0001

Data Index: 1451740 (Python Code)

Max Activating Token Index: 142

Text #1

Max Range: 1.4197. Min Range: -1.4197

Max Act: 1.3370. Min Act: -0.0001

Data Index: 1518070 (Python Code)

Max Activating Token Index: 242

Text #2

Max Range: 1.4197. Min Range: -1.4197

Max Act: 1.1930. Min Act: -0.0001

Data Index: 433255 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 1.4197. Min Range: -1.4197

Max Act: 1.2127. Min Act: -0.0000

Data Index: 1444862 (Python Code)

Max Activating Token Index: 175

Text #4

Max Range: 1.4197. Min Range: -1.4197

Max Act: 1.1555. Min Act: -0.0000

Data Index: 1399166 (Python Code)

Max Activating Token Index: 269

Text #5

Max Range: 1.4197. Min Range: -1.4197

Max Act: 1.0903. Min Act: -0.0001

Data Index: 1493483 (Python Code)

Max Activating Token Index: 103

Text #6

Max Range: 1.4197. Min Range: -1.4197

Max Act: 1.0341. Min Act: -0.0001

Data Index: 1559612 (Python Code)

Max Activating Token Index: 1018

Text #7

Max Range: 1.4197. Min Range: -1.4197

Max Act: 1.0376. Min Act: -0.0000

Data Index: 1098664 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 1.4197. Min Range: -1.4197

Max Act: 1.0410. Min Act: -0.0001

Data Index: 300024 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 1.4197. Min Range: -1.4197

Max Act: 1.0046. Min Act: -0.0000

Data Index: 1457733 (Python Code)

Max Activating Token Index: 722

Text #10

Max Range: 1.4197. Min Range: -1.4197

Max Act: 0.9290. Min Act: -0.0001

Data Index: 1440707 (Python Code)

Max Activating Token Index: 48

Text #11

Max Range: 1.4197. Min Range: -1.4197

Max Act: 0.9526. Min Act: -0.0001

Data Index: 1445101 (Python Code)

Max Activating Token Index: 838

Text #12

Max Range: 1.4197. Min Range: -1.4197

Max Act: 0.9606. Min Act: -0.0000

Data Index: 1516825 (Python Code)

Max Activating Token Index: 172

Text #13

Max Range: 1.4197. Min Range: -1.4197

Max Act: 0.9572. Min Act: -0.0000

Data Index: 1621380 (Python Code)

Max Activating Token Index: 177

Text #14

Max Range: 1.4197. Min Range: -1.4197

Max Act: 0.8820. Min Act: -0.0001

Data Index: 1508892 (Python Code)

Max Activating Token Index: 301

Text #15

Max Range: 1.4197. Min Range: -1.4197

Max Act: 0.8867. Min Act: -0.0001

Data Index: 1440850 (Python Code)

Max Activating Token Index: 110

Text #16

Max Range: 1.4197. Min Range: -1.4197

Max Act: 0.8655. Min Act: -0.0001

Data Index: 1655841 (Python Code)

Max Activating Token Index: 473

Text #17

Max Range: 1.4197. Min Range: -1.4197

Max Act: 0.9139. Min Act: -0.0000

Data Index: 559164 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 1.4197. Min Range: -1.4197

Max Act: 0.8435. Min Act: -0.0001

Data Index: 1502429 (Python Code)

Max Activating Token Index: 719

Text #19

Max Range: 1.4197. Min Range: -1.4197

Max Act: 0.8516. Min Act: -0.0001

Data Index: 1603674 (Python Code)

Max Activating Token Index: 979