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

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

Neuron 6076 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: 3.0536. Min Range: -3.0536

Max Act: 3.0536. Min Act: -0.0000

Data Index: 385131 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 3.0536. Min Range: -3.0536

Max Act: 2.7648. Min Act: -0.0000

Data Index: 636769 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 3.0536. Min Range: -3.0536

Max Act: 2.5944. Min Act: -0.0000

Data Index: 1078342 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 3.0536. Min Range: -3.0536

Max Act: 2.5448. Min Act: -0.0000

Data Index: 4288 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 3.0536. Min Range: -3.0536

Max Act: 2.3143. Min Act: -0.0000

Data Index: 918993 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 3.0536. Min Range: -3.0536

Max Act: 2.1941. Min Act: -0.0000

Data Index: 579305 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 3.0536. Min Range: -3.0536

Max Act: 2.3055. Min Act: -0.0000

Data Index: 1242039 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 3.0536. Min Range: -3.0536

Max Act: 2.2771. Min Act: -0.0000

Data Index: 638182 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 3.0536. Min Range: -3.0536

Max Act: 2.1264. Min Act: -0.0000

Data Index: 170848 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 3.0536. Min Range: -3.0536

Max Act: 2.2800. Min Act: -0.0000

Data Index: 1189701 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 3.0536. Min Range: -3.0536

Max Act: 2.2527. Min Act: -0.0000

Data Index: 634763 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 3.0536. Min Range: -3.0536

Max Act: 2.1092. Min Act: -0.0000

Data Index: 437808 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 3.0536. Min Range: -3.0536

Max Act: 2.3426. Min Act: -0.0000

Data Index: 358664 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 3.0536. Min Range: -3.0536

Max Act: 2.2212. Min Act: -0.0000

Data Index: 918971 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 3.0536. Min Range: -3.0536

Max Act: 2.0797. Min Act: -0.0000

Data Index: 801437 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 3.0536. Min Range: -3.0536

Max Act: 2.1704. Min Act: -0.0000

Data Index: 1172706 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 3.0536. Min Range: -3.0536

Max Act: 2.1514. Min Act: -0.0000

Data Index: 625789 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 3.0536. Min Range: -3.0536

Max Act: 2.0457. Min Act: -0.0000

Data Index: 26681 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 3.0536. Min Range: -3.0536

Max Act: 2.2539. Min Act: -0.0000

Data Index: 195736 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 3.0536. Min Range: -3.0536

Max Act: 2.2367. Min Act: -0.0000

Data Index: 32110 (C4 (Web Text))

Max Activating Token Index: 636