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

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

Neuron 614 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: 2.2197. Min Range: -2.2197

Max Act: 2.2197. Min Act: -0.0002

Data Index: 102887 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 2.2197. Min Range: -2.2197

Max Act: 2.1115. Min Act: -0.0002

Data Index: 169077 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 2.2197. Min Range: -2.2197

Max Act: 2.0584. Min Act: -0.0002

Data Index: 1274360 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 2.2197. Min Range: -2.2197

Max Act: 2.1341. Min Act: -0.0002

Data Index: 186178 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 2.2197. Min Range: -2.2197

Max Act: 2.0700. Min Act: -0.0002

Data Index: 788184 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 2.2197. Min Range: -2.2197

Max Act: 2.0504. Min Act: -0.0003

Data Index: 25859 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 2.2197. Min Range: -2.2197

Max Act: 2.0050. Min Act: -0.0002

Data Index: 382932 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 2.2197. Min Range: -2.2197

Max Act: 1.9974. Min Act: -0.0002

Data Index: 377949 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 2.2197. Min Range: -2.2197

Max Act: 1.9637. Min Act: -0.0002

Data Index: 915487 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 2.2197. Min Range: -2.2197

Max Act: 2.0051. Min Act: -0.0003

Data Index: 853958 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 2.2197. Min Range: -2.2197

Max Act: 1.9438. Min Act: -0.0002

Data Index: 200569 (C4 (Web Text))

Max Activating Token Index: 590

Text #11

Max Range: 2.2197. Min Range: -2.2197

Max Act: 1.9313. Min Act: -0.0003

Data Index: 109537 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 2.2197. Min Range: -2.2197

Max Act: 1.8958. Min Act: -0.0002

Data Index: 293835 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 2.2197. Min Range: -2.2197

Max Act: 1.8941. Min Act: -0.0002

Data Index: 873839 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 2.2197. Min Range: -2.2197

Max Act: 1.8600. Min Act: -0.0002

Data Index: 204598 (C4 (Web Text))

Max Activating Token Index: 365

Text #15

Max Range: 2.2197. Min Range: -2.2197

Max Act: 1.8665. Min Act: -0.0002

Data Index: 358835 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 2.2197. Min Range: -2.2197

Max Act: 1.8679. Min Act: -0.0003

Data Index: 1325326 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 2.2197. Min Range: -2.2197

Max Act: 1.8609. Min Act: -0.0002

Data Index: 190429 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 2.2197. Min Range: -2.2197

Max Act: 1.8938. Min Act: -0.0002

Data Index: 138613 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 2.2197. Min Range: -2.2197

Max Act: 1.8098. Min Act: -0.0002

Data Index: 56673 (C4 (Web Text))

Max Activating Token Index: 825