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

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

Neuron 2303 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.3020. Min Act: -0.0000

Data Index: 499014 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2290. Min Act: -0.0000

Data Index: 289868 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2532. Min Act: -0.0001

Data Index: 40356 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2261. Min Act: -0.0000

Data Index: 198681 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2049. Min Act: -0.0001

Data Index: 805787 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2025. Min Act: -0.0001

Data Index: 207466 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2045. Min Act: -0.0000

Data Index: 1028448 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.1655. Min Act: -0.0000

Data Index: 1176170 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.1795. Min Act: -0.0000

Data Index: 87480 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.1662. Min Act: -0.0000

Data Index: 494390 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.1585. Min Act: -0.0000

Data Index: 387129 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.1545. Min Act: -0.0001

Data Index: 1003366 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.1412. Min Act: -0.0000

Data Index: 285165 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.1472. Min Act: -0.0000

Data Index: 973602 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.1501. Min Act: -0.0000

Data Index: 870689 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.1449. Min Act: -0.0000

Data Index: 552202 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.1569. Min Act: -0.0001

Data Index: 210560 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.1460. Min Act: -0.0000

Data Index: 365379 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.1545. Min Act: -0.0000

Data Index: 172201 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.1385. Min Act: -0.0001

Data Index: 276989 (C4 (Web Text))

Max Activating Token Index: 553