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

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

Neuron 4894 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: 1.9554. Min Range: -1.9554

Max Act: 1.9554. Min Act: -0.0000

Data Index: 38098 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 1.9554. Min Range: -1.9554

Max Act: 1.9064. Min Act: -0.0000

Data Index: 1259580 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 1.9554. Min Range: -1.9554

Max Act: 1.7904. Min Act: -0.0001

Data Index: 1119062 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 1.9554. Min Range: -1.9554

Max Act: 1.8697. Min Act: -0.0000

Data Index: 1198048 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 1.9554. Min Range: -1.9554

Max Act: 1.8166. Min Act: -0.0000

Data Index: 563593 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 1.9554. Min Range: -1.9554

Max Act: 1.7833. Min Act: -0.0000

Data Index: 545884 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 1.9554. Min Range: -1.9554

Max Act: 1.7093. Min Act: -0.0000

Data Index: 1349197 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 1.9554. Min Range: -1.9554

Max Act: 1.8129. Min Act: -0.0000

Data Index: 201515 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 1.9554. Min Range: -1.9554

Max Act: 1.6844. Min Act: -0.0000

Data Index: 373443 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 1.9554. Min Range: -1.9554

Max Act: 1.7837. Min Act: -0.0000

Data Index: 198972 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 1.9554. Min Range: -1.9554

Max Act: 1.6440. Min Act: -0.0001

Data Index: 783562 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 1.9554. Min Range: -1.9554

Max Act: 1.6034. Min Act: -0.0000

Data Index: 139002 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 1.9554. Min Range: -1.9554

Max Act: 1.6919. Min Act: -0.0000

Data Index: 856900 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 1.9554. Min Range: -1.9554

Max Act: 1.6327. Min Act: -0.0000

Data Index: 1351956 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 1.9554. Min Range: -1.9554

Max Act: 1.4349. Min Act: -0.0000

Data Index: 482393 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 1.9554. Min Range: -1.9554

Max Act: 1.6195. Min Act: -0.0000

Data Index: 778323 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 1.9554. Min Range: -1.9554

Max Act: 1.5332. Min Act: -0.0000

Data Index: 1063840 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 1.9554. Min Range: -1.9554

Max Act: 1.5683. Min Act: -0.0000

Data Index: 317523 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 1.9554. Min Range: -1.9554

Max Act: 1.5249. Min Act: -0.0000

Data Index: 978757 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 1.9554. Min Range: -1.9554

Max Act: 1.5873. Min Act: -0.0000

Data Index: 530331 (C4 (Web Text))

Max Activating Token Index: 30