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

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

Neuron 1548 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.8302. Min Range: -6.8302

Max Act: 6.6809. Min Act: -0.0000

Data Index: 277378 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 6.8302. Min Range: -6.8302

Max Act: 6.8302. Min Act: -0.0000

Data Index: 1318095 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 6.8302. Min Range: -6.8302

Max Act: 6.3730. Min Act: -0.0000

Data Index: 651758 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 6.8302. Min Range: -6.8302

Max Act: 6.5467. Min Act: -0.0000

Data Index: 618444 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 6.8302. Min Range: -6.8302

Max Act: 6.2707. Min Act: -0.0000

Data Index: 1215651 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 6.8302. Min Range: -6.8302

Max Act: 6.3079. Min Act: -0.0000

Data Index: 689850 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 6.8302. Min Range: -6.8302

Max Act: 6.2662. Min Act: -0.0000

Data Index: 429376 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 6.8302. Min Range: -6.8302

Max Act: 5.7747. Min Act: -0.0000

Data Index: 1036914 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 6.8302. Min Range: -6.8302

Max Act: 6.1300. Min Act: -0.0000

Data Index: 1033926 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 6.8302. Min Range: -6.8302

Max Act: 6.3175. Min Act: -0.0000

Data Index: 129236 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 6.8302. Min Range: -6.8302

Max Act: 5.8387. Min Act: -0.0000

Data Index: 454771 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 6.8302. Min Range: -6.8302

Max Act: 6.2408. Min Act: -0.0000

Data Index: 188605 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 6.8302. Min Range: -6.8302

Max Act: 6.0708. Min Act: -0.0000

Data Index: 620499 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 6.8302. Min Range: -6.8302

Max Act: 5.7271. Min Act: -0.0000

Data Index: 81480 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 6.8302. Min Range: -6.8302

Max Act: 5.8457. Min Act: -0.0000

Data Index: 315617 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 6.8302. Min Range: -6.8302

Max Act: 5.4145. Min Act: -0.0000

Data Index: 30164 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 6.8302. Min Range: -6.8302

Max Act: 5.4378. Min Act: -0.0000

Data Index: 998952 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 6.8302. Min Range: -6.8302

Max Act: 5.4006. Min Act: -0.0000

Data Index: 231509 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 6.8302. Min Range: -6.8302

Max Act: 5.3501. Min Act: -0.0000

Data Index: 647056 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 6.8302. Min Range: -6.8302

Max Act: 5.0818. Min Act: -0.0000

Data Index: 1162454 (C4 (Web Text))

Max Activating Token Index: 356