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

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

Neuron 2562 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1425. Min Range: -2.1425

Max Act: 2.1425. Min Act: -0.0000

Data Index: 337684 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 2.1425. Min Range: -2.1425

Max Act: 2.1059. Min Act: -0.0000

Data Index: 1086075 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 2.1425. Min Range: -2.1425

Max Act: 1.7816. Min Act: -0.0000

Data Index: 820494 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 2.1425. Min Range: -2.1425

Max Act: 1.7187. Min Act: -0.0000

Data Index: 936603 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 2.1425. Min Range: -2.1425

Max Act: 1.8160. Min Act: 0.0000

Data Index: 268108 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 2.1425. Min Range: -2.1425

Max Act: 1.8084. Min Act: -0.0000

Data Index: 296218 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 2.1425. Min Range: -2.1425

Max Act: 1.8741. Min Act: -0.0000

Data Index: 1063430 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 2.1425. Min Range: -2.1425

Max Act: 1.7565. Min Act: -0.0000

Data Index: 1153642 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 2.1425. Min Range: -2.1425

Max Act: 1.7907. Min Act: -0.0000

Data Index: 89442 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 2.1425. Min Range: -2.1425

Max Act: 1.6590. Min Act: -0.0000

Data Index: 1060586 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 2.1425. Min Range: -2.1425

Max Act: 1.5516. Min Act: -0.0000

Data Index: 446053 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 2.1425. Min Range: -2.1425

Max Act: 1.6386. Min Act: -0.0000

Data Index: 644400 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 2.1425. Min Range: -2.1425

Max Act: 1.6252. Min Act: -0.0000

Data Index: 1074539 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 2.1425. Min Range: -2.1425

Max Act: 1.6189. Min Act: -0.0000

Data Index: 592300 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 2.1425. Min Range: -2.1425

Max Act: 1.5626. Min Act: -0.0000

Data Index: 1353459 (C4 (Web Text))

Max Activating Token Index: 181

Text #15

Max Range: 2.1425. Min Range: -2.1425

Max Act: 1.5293. Min Act: -0.0000

Data Index: 1052404 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 2.1425. Min Range: -2.1425

Max Act: 1.6172. Min Act: -0.0000

Data Index: 286672 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 2.1425. Min Range: -2.1425

Max Act: 1.5146. Min Act: -0.0000

Data Index: 529931 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 2.1425. Min Range: -2.1425

Max Act: 1.4993. Min Act: -0.0000

Data Index: 388437 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 2.1425. Min Range: -2.1425

Max Act: 1.5591. Min Act: -0.0000

Data Index: 399253 (C4 (Web Text))

Max Activating Token Index: 274