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

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

Neuron 3301 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.4224. Min Range: -1.4224

Max Act: 1.4224. Min Act: -0.0002

Data Index: 803287 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 1.4224. Min Range: -1.4224

Max Act: 1.3453. Min Act: -0.0002

Data Index: 1120138 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 1.4224. Min Range: -1.4224

Max Act: 1.3645. Min Act: -0.0002

Data Index: 562367 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 1.4224. Min Range: -1.4224

Max Act: 1.3616. Min Act: -0.0002

Data Index: 491535 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 1.4224. Min Range: -1.4224

Max Act: 1.3340. Min Act: -0.0002

Data Index: 9775 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 1.4224. Min Range: -1.4224

Max Act: 1.3214. Min Act: -0.0002

Data Index: 877422 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 1.4224. Min Range: -1.4224

Max Act: 1.3394. Min Act: -0.0002

Data Index: 229267 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 1.4224. Min Range: -1.4224

Max Act: 1.3162. Min Act: -0.0002

Data Index: 226085 (C4 (Web Text))

Max Activating Token Index: 329

Text #8

Max Range: 1.4224. Min Range: -1.4224

Max Act: 1.3148. Min Act: -0.0002

Data Index: 516430 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 1.4224. Min Range: -1.4224

Max Act: 1.3031. Min Act: -0.0002

Data Index: 452605 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 1.4224. Min Range: -1.4224

Max Act: 1.2518. Min Act: -0.0002

Data Index: 825084 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 1.4224. Min Range: -1.4224

Max Act: 1.2900. Min Act: -0.0002

Data Index: 808594 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 1.4224. Min Range: -1.4224

Max Act: 1.2795. Min Act: -0.0002

Data Index: 312054 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 1.4224. Min Range: -1.4224

Max Act: 1.3089. Min Act: -0.0002

Data Index: 385528 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 1.4224. Min Range: -1.4224

Max Act: 1.2637. Min Act: -0.0003

Data Index: 339534 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 1.4224. Min Range: -1.4224

Max Act: 1.2930. Min Act: -0.0002

Data Index: 1015569 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 1.4224. Min Range: -1.4224

Max Act: 1.2446. Min Act: -0.0002

Data Index: 576879 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 1.4224. Min Range: -1.4224

Max Act: 1.2818. Min Act: -0.0002

Data Index: 826329 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 1.4224. Min Range: -1.4224

Max Act: 1.2913. Min Act: -0.0002

Data Index: 478833 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 1.4224. Min Range: -1.4224

Max Act: 1.2635. Min Act: -0.0002

Data Index: 1120037 (C4 (Web Text))

Max Activating Token Index: 526