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

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

Neuron 4284 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.8199. Min Act: -0.0000

Data Index: 243106 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.9651. Min Act: -0.0000

Data Index: 180506 (C4 (Web Text))

Max Activating Token Index: 879

Text #2

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.8380. Min Act: -0.0000

Data Index: 738918 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.5761. Min Act: -0.0000

Data Index: 902088 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.5909. Min Act: -0.0000

Data Index: 1074359 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.5733. Min Act: -0.0000

Data Index: 1030616 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.5595. Min Act: -0.0000

Data Index: 808087 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.5553. Min Act: -0.0000

Data Index: 1294864 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.5797. Min Act: -0.0000

Data Index: 1273397 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.5276. Min Act: -0.0000

Data Index: 1338257 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.4338. Min Act: -0.0000

Data Index: 358782 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.4086. Min Act: -0.0000

Data Index: 160464 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.4927. Min Act: -0.0000

Data Index: 647172 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.4511. Min Act: -0.0000

Data Index: 126155 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.5080. Min Act: -0.0000

Data Index: 580979 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.3798. Min Act: -0.0000

Data Index: 430281 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.3915. Min Act: -0.0000

Data Index: 703028 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.3740. Min Act: -0.0000

Data Index: 614883 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.2934. Min Act: -0.0000

Data Index: 1022174 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.4406. Min Act: -0.0000

Data Index: 236501 (C4 (Web Text))

Max Activating Token Index: 44