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

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

Neuron 2251 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0551. Min Range: -1.0551

Max Act: 1.0551. Min Act: -0.0001

Data Index: 704172 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.8581. Min Act: -0.0001

Data Index: 1310784 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.9055. Min Act: -0.0001

Data Index: 294248 (C4 (Web Text))

Max Activating Token Index: 430

Text #3

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.9489. Min Act: -0.0001

Data Index: 614777 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.7654. Min Act: -0.0001

Data Index: 375969 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.8266. Min Act: -0.0001

Data Index: 407413 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.7765. Min Act: -0.0001

Data Index: 827643 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.8152. Min Act: -0.0001

Data Index: 657977 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.7834. Min Act: -0.0001

Data Index: 1131534 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.8153. Min Act: -0.0001

Data Index: 139257 (C4 (Web Text))

Max Activating Token Index: 76

Text #10

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.7685. Min Act: -0.0001

Data Index: 294458 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.7682. Min Act: -0.0001

Data Index: 520466 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.7276. Min Act: -0.0001

Data Index: 444931 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.7368. Min Act: -0.0001

Data Index: 1016754 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.7039. Min Act: -0.0001

Data Index: 668605 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.7032. Min Act: -0.0001

Data Index: 419713 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.7022. Min Act: -0.0001

Data Index: 713214 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.7496. Min Act: -0.0001

Data Index: 506114 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.6747. Min Act: -0.0001

Data Index: 972818 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 1.0551. Min Range: -1.0551

Max Act: 0.7000. Min Act: -0.0001

Data Index: 757506 (C4 (Web Text))

Max Activating Token Index: 722