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

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

Neuron 2326 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: 1.2872. Min Range: -1.2872

Max Act: 1.2131. Min Act: -0.0000

Data Index: 563750 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 1.2872. Min Range: -1.2872

Max Act: 1.1585. Min Act: -0.0000

Data Index: 1212481 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 1.2872. Min Range: -1.2872

Max Act: 1.1426. Min Act: -0.0000

Data Index: 919111 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 1.2872. Min Range: -1.2872

Max Act: 0.9786. Min Act: -0.0000

Data Index: 984921 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 1.2872. Min Range: -1.2872

Max Act: 0.9827. Min Act: -0.0000

Data Index: 908609 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 1.2872. Min Range: -1.2872

Max Act: 1.2872. Min Act: -0.0000

Data Index: 377935 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 1.2872. Min Range: -1.2872

Max Act: 1.0711. Min Act: -0.0000

Data Index: 393911 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 1.2872. Min Range: -1.2872

Max Act: 0.9246. Min Act: -0.0000

Data Index: 462878 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 1.2872. Min Range: -1.2872

Max Act: 0.8120. Min Act: -0.0000

Data Index: 390918 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 1.2872. Min Range: -1.2872

Max Act: 0.7552. Min Act: -0.0000

Data Index: 586128 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 1.2872. Min Range: -1.2872

Max Act: 0.8226. Min Act: -0.0000

Data Index: 776661 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 1.2872. Min Range: -1.2872

Max Act: 0.6967. Min Act: -0.0000

Data Index: 733157 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 1.2872. Min Range: -1.2872

Max Act: 0.7562. Min Act: -0.0000

Data Index: 263684 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 1.2872. Min Range: -1.2872

Max Act: 0.7555. Min Act: -0.0000

Data Index: 770104 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 1.2872. Min Range: -1.2872

Max Act: 0.7095. Min Act: -0.0000

Data Index: 970761 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 1.2872. Min Range: -1.2872

Max Act: 0.7205. Min Act: -0.0000

Data Index: 1140438 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 1.2872. Min Range: -1.2872

Max Act: 0.7608. Min Act: -0.0000

Data Index: 829443 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 1.2872. Min Range: -1.2872

Max Act: 0.6271. Min Act: -0.0000

Data Index: 349331 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 1.2872. Min Range: -1.2872

Max Act: 0.6813. Min Act: -0.0000

Data Index: 1212933 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 1.2872. Min Range: -1.2872

Max Act: 0.7039. Min Act: -0.0000

Data Index: 70317 (C4 (Web Text))

Max Activating Token Index: 282