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

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

Neuron 1580 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5102. Min Range: -4.5102

Max Act: 4.5102. Min Act: -0.0000

Data Index: 463662 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 4.5102. Min Range: -4.5102

Max Act: 4.2079. Min Act: -0.0000

Data Index: 287317 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 4.5102. Min Range: -4.5102

Max Act: 3.6497. Min Act: -0.0000

Data Index: 1314853 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 4.5102. Min Range: -4.5102

Max Act: 3.3872. Min Act: -0.0000

Data Index: 1128994 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 4.5102. Min Range: -4.5102

Max Act: 3.3336. Min Act: -0.0000

Data Index: 785442 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 4.5102. Min Range: -4.5102

Max Act: 3.1448. Min Act: -0.0000

Data Index: 394763 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 4.5102. Min Range: -4.5102

Max Act: 3.4198. Min Act: -0.0000

Data Index: 520488 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 4.5102. Min Range: -4.5102

Max Act: 3.2563. Min Act: -0.0000

Data Index: 1155520 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 4.5102. Min Range: -4.5102

Max Act: 2.9340. Min Act: -0.0000

Data Index: 579268 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 4.5102. Min Range: -4.5102

Max Act: 3.3596. Min Act: -0.0000

Data Index: 1343188 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 4.5102. Min Range: -4.5102

Max Act: 3.2064. Min Act: -0.0000

Data Index: 1275144 (C4 (Web Text))

Max Activating Token Index: 828

Text #11

Max Range: 4.5102. Min Range: -4.5102

Max Act: 3.1298. Min Act: -0.0000

Data Index: 618264 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 4.5102. Min Range: -4.5102

Max Act: 3.2971. Min Act: -0.0000

Data Index: 885733 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 4.5102. Min Range: -4.5102

Max Act: 2.9563. Min Act: -0.0000

Data Index: 854652 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 4.5102. Min Range: -4.5102

Max Act: 3.2338. Min Act: -0.0000

Data Index: 1322083 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 4.5102. Min Range: -4.5102

Max Act: 3.0370. Min Act: -0.0000

Data Index: 94996 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 4.5102. Min Range: -4.5102

Max Act: 3.0429. Min Act: -0.0000

Data Index: 70816 (C4 (Web Text))

Max Activating Token Index: 997

Text #17

Max Range: 4.5102. Min Range: -4.5102

Max Act: 2.7314. Min Act: -0.0000

Data Index: 1413952 (Python Code)

Max Activating Token Index: 820

Text #18

Max Range: 4.5102. Min Range: -4.5102

Max Act: 2.8390. Min Act: -0.0000

Data Index: 648718 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 4.5102. Min Range: -4.5102

Max Act: 2.9621. Min Act: -0.0000

Data Index: 508826 (C4 (Web Text))

Max Activating Token Index: 526