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

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

Neuron 3007 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.5423. Min Act: -0.0000

Data Index: 284754 (C4 (Web Text))

Max Activating Token Index: 453

Text #1

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.5144. Min Act: -0.0000

Data Index: 783139 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.5074. Min Act: -0.0000

Data Index: 511821 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4963. Min Act: -0.0000

Data Index: 297398 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4714. Min Act: -0.0000

Data Index: 833572 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4464. Min Act: -0.0000

Data Index: 61901 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4432. Min Act: -0.0000

Data Index: 136236 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4287. Min Act: -0.0000

Data Index: 512606 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4334. Min Act: -0.0000

Data Index: 401132 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4353. Min Act: -0.0000

Data Index: 1312338 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4229. Min Act: -0.0000

Data Index: 88800 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4102. Min Act: -0.0000

Data Index: 1344515 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4260. Min Act: -0.0000

Data Index: 503525 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4120. Min Act: -0.0000

Data Index: 183898 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4000. Min Act: -0.0000

Data Index: 187904 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4140. Min Act: -0.0000

Data Index: 763171 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3992. Min Act: -0.0000

Data Index: 902162 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4091. Min Act: -0.0000

Data Index: 1035717 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4081. Min Act: -0.0000

Data Index: 413973 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4078. Min Act: -0.0000

Data Index: 1210365 (C4 (Web Text))

Max Activating Token Index: 126