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

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

Neuron 596 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: 2.2788. Min Range: -2.2788

Max Act: 2.2788. Min Act: -0.0000

Data Index: 861382 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 2.2788. Min Range: -2.2788

Max Act: 2.2481. Min Act: -0.0001

Data Index: 1195077 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 2.2788. Min Range: -2.2788

Max Act: 2.2017. Min Act: -0.0000

Data Index: 576724 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 2.2788. Min Range: -2.2788

Max Act: 2.0310. Min Act: -0.0000

Data Index: 629045 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 2.2788. Min Range: -2.2788

Max Act: 2.0486. Min Act: -0.0000

Data Index: 1232579 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 2.2788. Min Range: -2.2788

Max Act: 2.0230. Min Act: -0.0000

Data Index: 688781 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 2.2788. Min Range: -2.2788

Max Act: 2.0995. Min Act: -0.0000

Data Index: 402165 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 2.2788. Min Range: -2.2788

Max Act: 1.6554. Min Act: -0.0000

Data Index: 1304932 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 2.2788. Min Range: -2.2788

Max Act: 1.8455. Min Act: -0.0000

Data Index: 637750 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 2.2788. Min Range: -2.2788

Max Act: 1.7655. Min Act: -0.0000

Data Index: 19200 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 2.2788. Min Range: -2.2788

Max Act: 1.7312. Min Act: -0.0000

Data Index: 1261793 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 2.2788. Min Range: -2.2788

Max Act: 1.7099. Min Act: -0.0000

Data Index: 363053 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 2.2788. Min Range: -2.2788

Max Act: 1.8947. Min Act: -0.0000

Data Index: 94793 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 2.2788. Min Range: -2.2788

Max Act: 1.6818. Min Act: -0.0000

Data Index: 170922 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 2.2788. Min Range: -2.2788

Max Act: 1.5717. Min Act: -0.0000

Data Index: 250360 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 2.2788. Min Range: -2.2788

Max Act: 1.6104. Min Act: -0.0000

Data Index: 503378 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 2.2788. Min Range: -2.2788

Max Act: 1.4343. Min Act: -0.0000

Data Index: 552863 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 2.2788. Min Range: -2.2788

Max Act: 1.6919. Min Act: -0.0000

Data Index: 376933 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 2.2788. Min Range: -2.2788

Max Act: 1.4861. Min Act: -0.0001

Data Index: 260449 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 2.2788. Min Range: -2.2788

Max Act: 1.3889. Min Act: -0.0000

Data Index: 1197183 (C4 (Web Text))

Max Activating Token Index: 169