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

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

Neuron 535 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3694. Min Range: -2.3694

Max Act: 2.3694. Min Act: -0.0000

Data Index: 76911 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 2.3694. Min Range: -2.3694

Max Act: 2.1513. Min Act: -0.0000

Data Index: 548839 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 2.3694. Min Range: -2.3694

Max Act: 2.0964. Min Act: -0.0000

Data Index: 1350234 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 2.3694. Min Range: -2.3694

Max Act: 2.0579. Min Act: -0.0000

Data Index: 1029101 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 2.3694. Min Range: -2.3694

Max Act: 1.9981. Min Act: -0.0000

Data Index: 589026 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 2.3694. Min Range: -2.3694

Max Act: 1.8892. Min Act: -0.0000

Data Index: 683726 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 2.3694. Min Range: -2.3694

Max Act: 1.8655. Min Act: -0.0000

Data Index: 1254141 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 2.3694. Min Range: -2.3694

Max Act: 1.8785. Min Act: -0.0000

Data Index: 925622 (C4 (Web Text))

Max Activating Token Index: 943

Text #8

Max Range: 2.3694. Min Range: -2.3694

Max Act: 1.8872. Min Act: -0.0000

Data Index: 971668 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 2.3694. Min Range: -2.3694

Max Act: 1.6250. Min Act: -0.0000

Data Index: 607448 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 2.3694. Min Range: -2.3694

Max Act: 1.9031. Min Act: -0.0000

Data Index: 111083 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 2.3694. Min Range: -2.3694

Max Act: 1.8089. Min Act: -0.0000

Data Index: 493857 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 2.3694. Min Range: -2.3694

Max Act: 1.7757. Min Act: -0.0000

Data Index: 94028 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 2.3694. Min Range: -2.3694

Max Act: 1.7543. Min Act: -0.0000

Data Index: 1212056 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 2.3694. Min Range: -2.3694

Max Act: 1.7588. Min Act: -0.0000

Data Index: 426549 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 2.3694. Min Range: -2.3694

Max Act: 1.6563. Min Act: -0.0000

Data Index: 1359112 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 2.3694. Min Range: -2.3694

Max Act: 1.6615. Min Act: -0.0000

Data Index: 550248 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 2.3694. Min Range: -2.3694

Max Act: 1.6408. Min Act: -0.0000

Data Index: 1018800 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 2.3694. Min Range: -2.3694

Max Act: 1.8400. Min Act: -0.0000

Data Index: 205742 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 2.3694. Min Range: -2.3694

Max Act: 1.7324. Min Act: -0.0000

Data Index: 490490 (C4 (Web Text))

Max Activating Token Index: 90