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

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

Neuron 956 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: 1.3773. Min Range: -1.3773

Max Act: 1.3773. Min Act: -0.0000

Data Index: 1463606 (Python Code)

Max Activating Token Index: 541

Text #1

Max Range: 1.3773. Min Range: -1.3773

Max Act: 0.9498. Min Act: -0.0000

Data Index: 1518460 (Python Code)

Max Activating Token Index: 881

Text #2

Max Range: 1.3773. Min Range: -1.3773

Max Act: 0.9382. Min Act: -0.0000

Data Index: 1628722 (Python Code)

Max Activating Token Index: 428

Text #3

Max Range: 1.3773. Min Range: -1.3773

Max Act: 0.9124. Min Act: -0.0000

Data Index: 1262391 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 1.3773. Min Range: -1.3773

Max Act: 0.7570. Min Act: -0.0000

Data Index: 1437330 (Python Code)

Max Activating Token Index: 510

Text #5

Max Range: 1.3773. Min Range: -1.3773

Max Act: 0.7581. Min Act: -0.0000

Data Index: 592261 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 1.3773. Min Range: -1.3773

Max Act: 0.6901. Min Act: -0.0000

Data Index: 893115 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 1.3773. Min Range: -1.3773

Max Act: 0.6651. Min Act: -0.0000

Data Index: 1582096 (Python Code)

Max Activating Token Index: 904

Text #8

Max Range: 1.3773. Min Range: -1.3773

Max Act: 0.7259. Min Act: -0.0000

Data Index: 1594561 (Python Code)

Max Activating Token Index: 557

Text #9

Max Range: 1.3773. Min Range: -1.3773

Max Act: 0.6372. Min Act: -0.0000

Data Index: 178507 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 1.3773. Min Range: -1.3773

Max Act: 0.6553. Min Act: -0.0000

Data Index: 425376 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 1.3773. Min Range: -1.3773

Max Act: 0.6492. Min Act: -0.0000

Data Index: 1220620 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 1.3773. Min Range: -1.3773

Max Act: 0.6064. Min Act: -0.0000

Data Index: 382728 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 1.3773. Min Range: -1.3773

Max Act: 0.6459. Min Act: -0.0000

Data Index: 1000409 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 1.3773. Min Range: -1.3773

Max Act: 0.6444. Min Act: -0.0000

Data Index: 1035359 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 1.3773. Min Range: -1.3773

Max Act: 0.6335. Min Act: -0.0000

Data Index: 919791 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 1.3773. Min Range: -1.3773

Max Act: 0.6044. Min Act: -0.0000

Data Index: 362208 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 1.3773. Min Range: -1.3773

Max Act: 0.6145. Min Act: -0.0000

Data Index: 1053818 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 1.3773. Min Range: -1.3773

Max Act: 0.5932. Min Act: -0.0000

Data Index: 1481333 (Python Code)

Max Activating Token Index: 924

Text #19

Max Range: 1.3773. Min Range: -1.3773

Max Act: 0.6102. Min Act: -0.0000

Data Index: 1318919 (C4 (Web Text))

Max Activating Token Index: 447