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

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

Neuron 1345 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.8014. Min Act: -0.0000

Data Index: 505047 (C4 (Web Text))

Max Activating Token Index: 603

Text #1

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.6216. Min Act: -0.0000

Data Index: 244047 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.5977. Min Act: -0.0000

Data Index: 112998 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.5712. Min Act: -0.0001

Data Index: 61956 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.5483. Min Act: -0.0000

Data Index: 356602 (C4 (Web Text))

Max Activating Token Index: 409

Text #5

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.5347. Min Act: -0.0000

Data Index: 1043251 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.5315. Min Act: -0.0000

Data Index: 1253262 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.5575. Min Act: -0.0000

Data Index: 1301706 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.5255. Min Act: -0.0000

Data Index: 895230 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.5392. Min Act: -0.0000

Data Index: 967098 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.5114. Min Act: -0.0000

Data Index: 259811 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.4974. Min Act: -0.0001

Data Index: 942335 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.5125. Min Act: -0.0000

Data Index: 385675 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.5236. Min Act: -0.0000

Data Index: 600778 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.4871. Min Act: -0.0000

Data Index: 190755 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.4962. Min Act: -0.0000

Data Index: 118232 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.4965. Min Act: -0.0001

Data Index: 614152 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.4777. Min Act: -0.0000

Data Index: 1143050 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.4899. Min Act: -0.0000

Data Index: 181331 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.4724. Min Act: -0.0000

Data Index: 132226 (C4 (Web Text))

Max Activating Token Index: 431