Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4928 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0354. Min Range: -2.0354

Max Act: 2.0354. Min Act: -0.0000

Data Index: 804883 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 2.0354. Min Range: -2.0354

Max Act: 1.9659. Min Act: -0.0000

Data Index: 1135 (C4 (Web Text))

Max Activating Token Index: 614

Text #2

Max Range: 2.0354. Min Range: -2.0354

Max Act: 1.5962. Min Act: 0.0000

Data Index: 449025 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 2.0354. Min Range: -2.0354

Max Act: 1.5793. Min Act: 0.0000

Data Index: 745904 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 2.0354. Min Range: -2.0354

Max Act: 1.3572. Min Act: -0.0000

Data Index: 1154936 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 2.0354. Min Range: -2.0354

Max Act: 1.2296. Min Act: -0.0000

Data Index: 1275805 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 2.0354. Min Range: -2.0354

Max Act: 1.0472. Min Act: 0.0000

Data Index: 276842 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 2.0354. Min Range: -2.0354

Max Act: 1.0124. Min Act: -0.0000

Data Index: 1184183 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 2.0354. Min Range: -2.0354

Max Act: 1.0034. Min Act: -0.0000

Data Index: 908182 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 2.0354. Min Range: -2.0354

Max Act: 0.9477. Min Act: -0.0000

Data Index: 1234128 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 2.0354. Min Range: -2.0354

Max Act: 0.9114. Min Act: -0.0000

Data Index: 1292585 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 2.0354. Min Range: -2.0354

Max Act: 0.9113. Min Act: -0.0000

Data Index: 1021970 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 2.0354. Min Range: -2.0354

Max Act: 0.9608. Min Act: -0.0000

Data Index: 461979 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 2.0354. Min Range: -2.0354

Max Act: 0.7635. Min Act: -0.0000

Data Index: 485313 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 2.0354. Min Range: -2.0354

Max Act: 0.8410. Min Act: -0.0000

Data Index: 844581 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 2.0354. Min Range: -2.0354

Max Act: 0.7788. Min Act: -0.0000

Data Index: 958423 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 2.0354. Min Range: -2.0354

Max Act: 0.8191. Min Act: -0.0000

Data Index: 175485 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 2.0354. Min Range: -2.0354

Max Act: 0.7183. Min Act: -0.0000

Data Index: 1091166 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 2.0354. Min Range: -2.0354

Max Act: 0.7374. Min Act: -0.0000

Data Index: 795301 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 2.0354. Min Range: -2.0354

Max Act: 0.6932. Min Act: -0.0000

Data Index: 770763 (C4 (Web Text))

Max Activating Token Index: 1015