Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2426 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7610. Min Range: -1.7610

Max Act: 1.5970. Min Act: -0.0000

Data Index: 1321162 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 1.7610. Min Range: -1.7610

Max Act: 1.7610. Min Act: -0.0000

Data Index: 12213 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 1.7610. Min Range: -1.7610

Max Act: 1.5625. Min Act: -0.0000

Data Index: 275176 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 1.7610. Min Range: -1.7610

Max Act: 1.6700. Min Act: -0.0000

Data Index: 191960 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 1.7610. Min Range: -1.7610

Max Act: 1.6253. Min Act: -0.0001

Data Index: 1257433 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 1.7610. Min Range: -1.7610

Max Act: 1.4841. Min Act: -0.0001

Data Index: 413824 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 1.7610. Min Range: -1.7610

Max Act: 1.4441. Min Act: -0.0001

Data Index: 1026702 (C4 (Web Text))

Max Activating Token Index: 352

Text #7

Max Range: 1.7610. Min Range: -1.7610

Max Act: 1.4145. Min Act: -0.0001

Data Index: 577795 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 1.7610. Min Range: -1.7610

Max Act: 1.3666. Min Act: -0.0001

Data Index: 1349930 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 1.7610. Min Range: -1.7610

Max Act: 1.4164. Min Act: -0.0001

Data Index: 1141344 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 1.7610. Min Range: -1.7610

Max Act: 1.2485. Min Act: -0.0000

Data Index: 304084 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 1.7610. Min Range: -1.7610

Max Act: 1.1746. Min Act: -0.0001

Data Index: 965810 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 1.7610. Min Range: -1.7610

Max Act: 1.1976. Min Act: -0.0000

Data Index: 41965 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 1.7610. Min Range: -1.7610

Max Act: 1.1685. Min Act: -0.0001

Data Index: 826019 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 1.7610. Min Range: -1.7610

Max Act: 1.3821. Min Act: -0.0001

Data Index: 689774 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 1.7610. Min Range: -1.7610

Max Act: 1.2675. Min Act: -0.0001

Data Index: 28545 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 1.7610. Min Range: -1.7610

Max Act: 1.2237. Min Act: -0.0001

Data Index: 369466 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 1.7610. Min Range: -1.7610

Max Act: 1.1644. Min Act: -0.0001

Data Index: 660034 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 1.7610. Min Range: -1.7610

Max Act: 1.1873. Min Act: -0.0001

Data Index: 683849 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 1.7610. Min Range: -1.7610

Max Act: 1.1507. Min Act: -0.0000

Data Index: 251177 (C4 (Web Text))

Max Activating Token Index: 761