Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 684 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 12.4293. Min Range: -12.4293

Max Act: 12.4293. Min Act: -0.0001

Data Index: 69045 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 12.4293. Min Range: -12.4293

Max Act: 11.3679. Min Act: -0.0001

Data Index: 671743 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 12.4293. Min Range: -12.4293

Max Act: 10.8640. Min Act: -0.0001

Data Index: 52835 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 12.4293. Min Range: -12.4293

Max Act: 11.0335. Min Act: -0.0001

Data Index: 283670 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 12.4293. Min Range: -12.4293

Max Act: 10.3160. Min Act: -0.0001

Data Index: 90020 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 12.4293. Min Range: -12.4293

Max Act: 10.1505. Min Act: -0.0001

Data Index: 751536 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 12.4293. Min Range: -12.4293

Max Act: 10.3607. Min Act: -0.0001

Data Index: 982939 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 12.4293. Min Range: -12.4293

Max Act: 10.2091. Min Act: -0.0001

Data Index: 632793 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 12.4293. Min Range: -12.4293

Max Act: 10.3611. Min Act: -0.0001

Data Index: 567954 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 12.4293. Min Range: -12.4293

Max Act: 9.8753. Min Act: -0.0001

Data Index: 465853 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 12.4293. Min Range: -12.4293

Max Act: 9.8194. Min Act: -0.0001

Data Index: 1154881 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 12.4293. Min Range: -12.4293

Max Act: 9.7375. Min Act: -0.0001

Data Index: 1306530 (C4 (Web Text))

Max Activating Token Index: 428

Text #12

Max Range: 12.4293. Min Range: -12.4293

Max Act: 9.9280. Min Act: -0.0001

Data Index: 915423 (C4 (Web Text))

Max Activating Token Index: 374

Text #13

Max Range: 12.4293. Min Range: -12.4293

Max Act: 10.0378. Min Act: -0.0001

Data Index: 382298 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 12.4293. Min Range: -12.4293

Max Act: 9.6666. Min Act: -0.0001

Data Index: 292359 (C4 (Web Text))

Max Activating Token Index: 753

Text #15

Max Range: 12.4293. Min Range: -12.4293

Max Act: 9.8813. Min Act: -0.0001

Data Index: 1076932 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 12.4293. Min Range: -12.4293

Max Act: 9.7406. Min Act: -0.0001

Data Index: 1290536 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 12.4293. Min Range: -12.4293

Max Act: 9.8782. Min Act: -0.0001

Data Index: 924184 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 12.4293. Min Range: -12.4293

Max Act: 9.4122. Min Act: -0.0001

Data Index: 739770 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 12.4293. Min Range: -12.4293

Max Act: 9.5820. Min Act: -0.0001

Data Index: 56978 (C4 (Web Text))

Max Activating Token Index: 446