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

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

Neuron 3390 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: 3.4432. Min Range: -3.4432

Max Act: 3.4432. Min Act: -0.0000

Data Index: 928689 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.9823. Min Act: -0.0000

Data Index: 859799 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 3.4432. Min Range: -3.4432

Max Act: 3.0245. Min Act: -0.0000

Data Index: 852562 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 3.4432. Min Range: -3.4432

Max Act: 3.1470. Min Act: -0.0000

Data Index: 483766 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.9961. Min Act: -0.0000

Data Index: 56782 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.9438. Min Act: -0.0000

Data Index: 616654 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.9162. Min Act: -0.0000

Data Index: 1257833 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 3.4432. Min Range: -3.4432

Max Act: 3.0591. Min Act: -0.0000

Data Index: 22325 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.8525. Min Act: -0.0000

Data Index: 31558 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.5731. Min Act: -0.0000

Data Index: 1124585 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.7763. Min Act: -0.0000

Data Index: 860169 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.6434. Min Act: -0.0000

Data Index: 1016087 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.7416. Min Act: -0.0000

Data Index: 498160 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.4502. Min Act: -0.0000

Data Index: 345884 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.5608. Min Act: -0.0000

Data Index: 841561 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.5428. Min Act: -0.0000

Data Index: 1296100 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.8084. Min Act: -0.0000

Data Index: 593584 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.5357. Min Act: -0.0000

Data Index: 548753 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.7791. Min Act: -0.0000

Data Index: 550100 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.6428. Min Act: -0.0000

Data Index: 840553 (C4 (Web Text))

Max Activating Token Index: 997