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

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

Neuron 4415 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.9051. Min Act: -0.0000

Data Index: 1350343 (C4 (Web Text))

Max Activating Token Index: 245

Text #1

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.9230. Min Act: -0.0000

Data Index: 15758 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.8051. Min Act: -0.0000

Data Index: 947599 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.8060. Min Act: -0.0000

Data Index: 904193 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7974. Min Act: -0.0000

Data Index: 1321084 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.8391. Min Act: -0.0000

Data Index: 79079 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7648. Min Act: -0.0000

Data Index: 1269550 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7919. Min Act: -0.0000

Data Index: 593373 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7583. Min Act: -0.0000

Data Index: 411694 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7740. Min Act: -0.0000

Data Index: 411206 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7322. Min Act: -0.0000

Data Index: 645733 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7330. Min Act: -0.0000

Data Index: 619037 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7293. Min Act: -0.0000

Data Index: 903337 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7243. Min Act: -0.0000

Data Index: 806317 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7428. Min Act: -0.0000

Data Index: 280632 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7119. Min Act: -0.0000

Data Index: 755211 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7076. Min Act: -0.0000

Data Index: 590888 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.6854. Min Act: -0.0000

Data Index: 816461 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.6789. Min Act: -0.0000

Data Index: 1127645 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7432. Min Act: -0.0000

Data Index: 156394 (C4 (Web Text))

Max Activating Token Index: 815