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

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

Neuron 3060 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5989. Min Range: -0.5989

Max Act: 0.5989. Min Act: -0.0001

Data Index: 284613 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 0.5989. Min Range: -0.5989

Max Act: 0.5694. Min Act: -0.0000

Data Index: 1030918 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 0.5989. Min Range: -0.5989

Max Act: 0.5482. Min Act: -0.0000

Data Index: 266977 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 0.5989. Min Range: -0.5989

Max Act: 0.5038. Min Act: -0.0001

Data Index: 422028 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 0.5989. Min Range: -0.5989

Max Act: 0.4957. Min Act: -0.0000

Data Index: 438477 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 0.5989. Min Range: -0.5989

Max Act: 0.5049. Min Act: -0.0001

Data Index: 153977 (C4 (Web Text))

Max Activating Token Index: 410

Text #6

Max Range: 0.5989. Min Range: -0.5989

Max Act: 0.5140. Min Act: -0.0001

Data Index: 16327 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 0.5989. Min Range: -0.5989

Max Act: 0.4803. Min Act: -0.0001

Data Index: 165778 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 0.5989. Min Range: -0.5989

Max Act: 0.5057. Min Act: -0.0000

Data Index: 799661 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 0.5989. Min Range: -0.5989

Max Act: 0.4955. Min Act: -0.0001

Data Index: 277249 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 0.5989. Min Range: -0.5989

Max Act: 0.4913. Min Act: -0.0001

Data Index: 221870 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 0.5989. Min Range: -0.5989

Max Act: 0.4937. Min Act: -0.0001

Data Index: 976502 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 0.5989. Min Range: -0.5989

Max Act: 0.4500. Min Act: -0.0001

Data Index: 948957 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 0.5989. Min Range: -0.5989

Max Act: 0.4586. Min Act: -0.0000

Data Index: 737289 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 0.5989. Min Range: -0.5989

Max Act: 0.4313. Min Act: -0.0001

Data Index: 851613 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 0.5989. Min Range: -0.5989

Max Act: 0.4551. Min Act: -0.0001

Data Index: 1083893 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 0.5989. Min Range: -0.5989

Max Act: 0.4400. Min Act: -0.0001

Data Index: 90978 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.5989. Min Range: -0.5989

Max Act: 0.4192. Min Act: -0.0001

Data Index: 387782 (C4 (Web Text))

Max Activating Token Index: 487

Text #18

Max Range: 0.5989. Min Range: -0.5989

Max Act: 0.4318. Min Act: -0.0001

Data Index: 224240 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 0.5989. Min Range: -0.5989

Max Act: 0.4308. Min Act: -0.0001

Data Index: 1118081 (C4 (Web Text))

Max Activating Token Index: 76