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

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

Neuron 1650 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.3140. Min Act: -0.0001

Data Index: 1194548 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.3220. Min Act: -0.0001

Data Index: 1216329 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2850. Min Act: -0.0001

Data Index: 377855 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2753. Min Act: -0.0000

Data Index: 378673 (C4 (Web Text))

Max Activating Token Index: 919

Text #4

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2715. Min Act: -0.0001

Data Index: 430426 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2719. Min Act: -0.0001

Data Index: 291502 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2697. Min Act: -0.0001

Data Index: 535830 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2841. Min Act: -0.0001

Data Index: 750819 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2530. Min Act: -0.0001

Data Index: 195312 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2616. Min Act: -0.0001

Data Index: 1099013 (C4 (Web Text))

Max Activating Token Index: 457

Text #10

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2754. Min Act: -0.0000

Data Index: 1080179 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2667. Min Act: -0.0001

Data Index: 113376 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2438. Min Act: -0.0001

Data Index: 983064 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2479. Min Act: -0.0001

Data Index: 79925 (C4 (Web Text))

Max Activating Token Index: 233

Text #14

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2387. Min Act: -0.0001

Data Index: 951459 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2442. Min Act: -0.0001

Data Index: 624083 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2613. Min Act: -0.0001

Data Index: 346525 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2417. Min Act: -0.0001

Data Index: 22746 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2334. Min Act: -0.0001

Data Index: 1177801 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2405. Min Act: -0.0000

Data Index: 24799 (C4 (Web Text))

Max Activating Token Index: 717