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

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

Neuron 3575 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0389. Min Range: -7.0389

Max Act: 7.0389. Min Act: -0.0000

Data Index: 198069 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 7.0389. Min Range: -7.0389

Max Act: 6.2148. Min Act: -0.0000

Data Index: 765770 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 7.0389. Min Range: -7.0389

Max Act: 6.0146. Min Act: -0.0000

Data Index: 528669 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 7.0389. Min Range: -7.0389

Max Act: 6.3033. Min Act: -0.0000

Data Index: 1092202 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 7.0389. Min Range: -7.0389

Max Act: 6.2542. Min Act: -0.0001

Data Index: 871635 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 7.0389. Min Range: -7.0389

Max Act: 6.3804. Min Act: -0.0000

Data Index: 325609 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 7.0389. Min Range: -7.0389

Max Act: 6.0257. Min Act: -0.0000

Data Index: 327059 (C4 (Web Text))

Max Activating Token Index: 797

Text #7

Max Range: 7.0389. Min Range: -7.0389

Max Act: 5.5808. Min Act: -0.0000

Data Index: 1253985 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 7.0389. Min Range: -7.0389

Max Act: 5.9138. Min Act: -0.0000

Data Index: 856978 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 7.0389. Min Range: -7.0389

Max Act: 5.6421. Min Act: -0.0000

Data Index: 1258387 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 7.0389. Min Range: -7.0389

Max Act: 5.6334. Min Act: -0.0000

Data Index: 427820 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 7.0389. Min Range: -7.0389

Max Act: 5.7738. Min Act: -0.0000

Data Index: 641832 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 7.0389. Min Range: -7.0389

Max Act: 5.7171. Min Act: -0.0000

Data Index: 859749 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 7.0389. Min Range: -7.0389

Max Act: 5.6898. Min Act: -0.0000

Data Index: 245487 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 7.0389. Min Range: -7.0389

Max Act: 5.6286. Min Act: -0.0000

Data Index: 812527 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 7.0389. Min Range: -7.0389

Max Act: 5.3797. Min Act: -0.0000

Data Index: 155500 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 7.0389. Min Range: -7.0389

Max Act: 5.5377. Min Act: -0.0000

Data Index: 420991 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 7.0389. Min Range: -7.0389

Max Act: 5.3147. Min Act: -0.0000

Data Index: 542433 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 7.0389. Min Range: -7.0389

Max Act: 5.6307. Min Act: -0.0000

Data Index: 557739 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 7.0389. Min Range: -7.0389

Max Act: 5.4413. Min Act: -0.0000

Data Index: 1031876 (C4 (Web Text))

Max Activating Token Index: 586