Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2368 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.3715. Min Act: -0.0004

Data Index: 1016569 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.2415. Min Act: -0.0004

Data Index: 727187 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.1634. Min Act: -0.0004

Data Index: 580981 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.1342. Min Act: -0.0004

Data Index: 1286110 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.0933. Min Act: -0.0004

Data Index: 540568 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.1902. Min Act: -0.0004

Data Index: 1321650 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.0679. Min Act: -0.0004

Data Index: 263263 (C4 (Web Text))

Max Activating Token Index: 468

Text #7

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.0694. Min Act: -0.0004

Data Index: 1009402 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 1.3715. Min Range: -1.3715

Max Act: 0.9626. Min Act: -0.0004

Data Index: 119036 (C4 (Web Text))

Max Activating Token Index: 913

Text #9

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.0111. Min Act: -0.0004

Data Index: 145126 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.0093. Min Act: -0.0004

Data Index: 528492 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 1.3715. Min Range: -1.3715

Max Act: 0.9780. Min Act: -0.0004

Data Index: 990702 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.0361. Min Act: -0.0004

Data Index: 343791 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.1395. Min Act: -0.0004

Data Index: 727173 (C4 (Web Text))

Max Activating Token Index: 563

Text #14

Max Range: 1.3715. Min Range: -1.3715

Max Act: 0.9115. Min Act: -0.0004

Data Index: 913575 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 1.3715. Min Range: -1.3715

Max Act: 0.9509. Min Act: -0.0004

Data Index: 1316202 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 1.3715. Min Range: -1.3715

Max Act: 0.9706. Min Act: -0.0004

Data Index: 78591 (C4 (Web Text))

Max Activating Token Index: 614

Text #17

Max Range: 1.3715. Min Range: -1.3715

Max Act: 0.9688. Min Act: -0.0004

Data Index: 717068 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 1.3715. Min Range: -1.3715

Max Act: 0.7845. Min Act: -0.0004

Data Index: 1014517 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 1.3715. Min Range: -1.3715

Max Act: 0.9302. Min Act: -0.0004

Data Index: 1123140 (C4 (Web Text))

Max Activating Token Index: 202