Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6134 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.1311. Min Range: -3.1311

Max Act: 3.1311. Min Act: -0.0000

Data Index: 471813 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 3.1311. Min Range: -3.1311

Max Act: 2.7378. Min Act: -0.0001

Data Index: 817030 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 3.1311. Min Range: -3.1311

Max Act: 2.3541. Min Act: -0.0001

Data Index: 260262 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 3.1311. Min Range: -3.1311

Max Act: 2.5672. Min Act: -0.0000

Data Index: 1244668 (C4 (Web Text))

Max Activating Token Index: 572

Text #4

Max Range: 3.1311. Min Range: -3.1311

Max Act: 2.3013. Min Act: -0.0001

Data Index: 506341 (C4 (Web Text))

Max Activating Token Index: 920

Text #5

Max Range: 3.1311. Min Range: -3.1311

Max Act: 2.1880. Min Act: -0.0000

Data Index: 748053 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 3.1311. Min Range: -3.1311

Max Act: 2.0716. Min Act: -0.0000

Data Index: 364664 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 3.1311. Min Range: -3.1311

Max Act: 2.1301. Min Act: -0.0000

Data Index: 583497 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 3.1311. Min Range: -3.1311

Max Act: 2.0070. Min Act: -0.0000

Data Index: 364380 (C4 (Web Text))

Max Activating Token Index: 747

Text #9

Max Range: 3.1311. Min Range: -3.1311

Max Act: 2.1125. Min Act: -0.0000

Data Index: 133417 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 3.1311. Min Range: -3.1311

Max Act: 2.2532. Min Act: -0.0001

Data Index: 468032 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 3.1311. Min Range: -3.1311

Max Act: 2.0897. Min Act: -0.0000

Data Index: 455611 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 3.1311. Min Range: -3.1311

Max Act: 2.0554. Min Act: -0.0000

Data Index: 1830 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 3.1311. Min Range: -3.1311

Max Act: 1.9362. Min Act: -0.0000

Data Index: 569536 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 3.1311. Min Range: -3.1311

Max Act: 2.2477. Min Act: -0.0000

Data Index: 1058700 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 3.1311. Min Range: -3.1311

Max Act: 2.0286. Min Act: -0.0000

Data Index: 357596 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 3.1311. Min Range: -3.1311

Max Act: 2.0141. Min Act: -0.0001

Data Index: 1181943 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 3.1311. Min Range: -3.1311

Max Act: 2.0759. Min Act: -0.0000

Data Index: 1152005 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 3.1311. Min Range: -3.1311

Max Act: 1.9181. Min Act: -0.0000

Data Index: 1354668 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 3.1311. Min Range: -3.1311

Max Act: 2.0140. Min Act: -0.0001

Data Index: 153717 (C4 (Web Text))

Max Activating Token Index: 68