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

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

Neuron 956 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7940. Min Range: -2.7940

Max Act: 2.7940. Min Act: -0.0000

Data Index: 301167 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 2.7940. Min Range: -2.7940

Max Act: 2.6833. Min Act: -0.0000

Data Index: 435277 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 2.7940. Min Range: -2.7940

Max Act: 2.4955. Min Act: -0.0000

Data Index: 1265718 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 2.7940. Min Range: -2.7940

Max Act: 2.5353. Min Act: -0.0000

Data Index: 790706 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 2.7940. Min Range: -2.7940

Max Act: 2.2228. Min Act: -0.0000

Data Index: 1147092 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 2.7940. Min Range: -2.7940

Max Act: 2.2395. Min Act: -0.0000

Data Index: 431923 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 2.7940. Min Range: -2.7940

Max Act: 2.1567. Min Act: -0.0000

Data Index: 804681 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 2.7940. Min Range: -2.7940

Max Act: 1.9711. Min Act: -0.0000

Data Index: 311172 (C4 (Web Text))

Max Activating Token Index: 785

Text #8

Max Range: 2.7940. Min Range: -2.7940

Max Act: 2.0663. Min Act: -0.0000

Data Index: 518123 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 2.7940. Min Range: -2.7940

Max Act: 2.0206. Min Act: -0.0000

Data Index: 1331082 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 2.7940. Min Range: -2.7940

Max Act: 1.9942. Min Act: -0.0000

Data Index: 255351 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 2.7940. Min Range: -2.7940

Max Act: 2.0403. Min Act: -0.0000

Data Index: 1344820 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 2.7940. Min Range: -2.7940

Max Act: 1.9497. Min Act: -0.0000

Data Index: 478351 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 2.7940. Min Range: -2.7940

Max Act: 1.8827. Min Act: -0.0000

Data Index: 1184866 (C4 (Web Text))

Max Activating Token Index: 379

Text #14

Max Range: 2.7940. Min Range: -2.7940

Max Act: 1.8621. Min Act: -0.0000

Data Index: 1197117 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 2.7940. Min Range: -2.7940

Max Act: 1.8606. Min Act: -0.0000

Data Index: 1237949 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 2.7940. Min Range: -2.7940

Max Act: 1.7348. Min Act: -0.0000

Data Index: 979471 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 2.7940. Min Range: -2.7940

Max Act: 1.4915. Min Act: -0.0000

Data Index: 1137037 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 2.7940. Min Range: -2.7940

Max Act: 1.1842. Min Act: -0.0000

Data Index: 74640 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 2.7940. Min Range: -2.7940

Max Act: 1.2600. Min Act: -0.0000

Data Index: 31752 (C4 (Web Text))

Max Activating Token Index: 840