Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1570 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4073. Min Range: -2.4073

Max Act: 2.4073. Min Act: -0.0000

Data Index: 520516 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 2.4073. Min Range: -2.4073

Max Act: 2.0514. Min Act: -0.0000

Data Index: 725036 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 2.4073. Min Range: -2.4073

Max Act: 2.0424. Min Act: -0.0000

Data Index: 1309430 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 2.4073. Min Range: -2.4073

Max Act: 1.9809. Min Act: -0.0000

Data Index: 1025318 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 2.4073. Min Range: -2.4073

Max Act: 1.9803. Min Act: -0.0000

Data Index: 456675 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 2.4073. Min Range: -2.4073

Max Act: 1.9721. Min Act: -0.0000

Data Index: 931431 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 2.4073. Min Range: -2.4073

Max Act: 1.8618. Min Act: -0.0000

Data Index: 105986 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 2.4073. Min Range: -2.4073

Max Act: 1.8388. Min Act: -0.0000

Data Index: 897601 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 2.4073. Min Range: -2.4073

Max Act: 2.0461. Min Act: -0.0000

Data Index: 28499 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 2.4073. Min Range: -2.4073

Max Act: 1.8388. Min Act: -0.0000

Data Index: 273102 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 2.4073. Min Range: -2.4073

Max Act: 1.8302. Min Act: -0.0000

Data Index: 760727 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 2.4073. Min Range: -2.4073

Max Act: 2.0153. Min Act: -0.0000

Data Index: 11361 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 2.4073. Min Range: -2.4073

Max Act: 1.9101. Min Act: -0.0000

Data Index: 1188512 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 2.4073. Min Range: -2.4073

Max Act: 1.9132. Min Act: -0.0000

Data Index: 263774 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 2.4073. Min Range: -2.4073

Max Act: 1.8068. Min Act: -0.0000

Data Index: 53808 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 2.4073. Min Range: -2.4073

Max Act: 1.7853. Min Act: -0.0000

Data Index: 593364 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 2.4073. Min Range: -2.4073

Max Act: 1.8792. Min Act: -0.0000

Data Index: 1231575 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 2.4073. Min Range: -2.4073

Max Act: 1.7504. Min Act: -0.0000

Data Index: 1305916 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 2.4073. Min Range: -2.4073

Max Act: 1.8484. Min Act: -0.0000

Data Index: 318864 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 2.4073. Min Range: -2.4073

Max Act: 1.8285. Min Act: -0.0000

Data Index: 1324592 (C4 (Web Text))

Max Activating Token Index: 817