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

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

Neuron 1445 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.8243. Min Range: -2.8243

Max Act: 2.8243. Min Act: -0.0000

Data Index: 517544 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 2.8243. Min Range: -2.8243

Max Act: 2.4114. Min Act: -0.0000

Data Index: 394224 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 2.8243. Min Range: -2.8243

Max Act: 2.2146. Min Act: -0.0000

Data Index: 112432 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 2.8243. Min Range: -2.8243

Max Act: 2.3024. Min Act: -0.0000

Data Index: 32052 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 2.8243. Min Range: -2.8243

Max Act: 2.1493. Min Act: -0.0000

Data Index: 604791 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 2.8243. Min Range: -2.8243

Max Act: 2.0799. Min Act: -0.0000

Data Index: 1398274 (Python Code)

Max Activating Token Index: 569

Text #6

Max Range: 2.8243. Min Range: -2.8243

Max Act: 1.9964. Min Act: -0.0000

Data Index: 1414477 (Python Code)

Max Activating Token Index: 862

Text #7

Max Range: 2.8243. Min Range: -2.8243

Max Act: 1.9960. Min Act: -0.0000

Data Index: 1606905 (Python Code)

Max Activating Token Index: 521

Text #8

Max Range: 2.8243. Min Range: -2.8243

Max Act: 1.9262. Min Act: -0.0000

Data Index: 1417828 (Python Code)

Max Activating Token Index: 543

Text #9

Max Range: 2.8243. Min Range: -2.8243

Max Act: 1.9569. Min Act: -0.0000

Data Index: 1502546 (Python Code)

Max Activating Token Index: 955

Text #10

Max Range: 2.8243. Min Range: -2.8243

Max Act: 1.9840. Min Act: -0.0000

Data Index: 1576739 (Python Code)

Max Activating Token Index: 367

Text #11

Max Range: 2.8243. Min Range: -2.8243

Max Act: 1.8304. Min Act: -0.0000

Data Index: 834220 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 2.8243. Min Range: -2.8243

Max Act: 1.9835. Min Act: -0.0000

Data Index: 182040 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 2.8243. Min Range: -2.8243

Max Act: 1.9770. Min Act: -0.0000

Data Index: 1627965 (Python Code)

Max Activating Token Index: 473

Text #14

Max Range: 2.8243. Min Range: -2.8243

Max Act: 2.0474. Min Act: -0.0000

Data Index: 1241747 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 2.8243. Min Range: -2.8243

Max Act: 1.8255. Min Act: -0.0000

Data Index: 815734 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 2.8243. Min Range: -2.8243

Max Act: 1.9749. Min Act: -0.0000

Data Index: 502753 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 2.8243. Min Range: -2.8243

Max Act: 1.7722. Min Act: -0.0000

Data Index: 1608496 (Python Code)

Max Activating Token Index: 658

Text #18

Max Range: 2.8243. Min Range: -2.8243

Max Act: 1.5444. Min Act: -0.0000

Data Index: 1368064 (Python Code)

Max Activating Token Index: 210

Text #19

Max Range: 2.8243. Min Range: -2.8243

Max Act: 1.8282. Min Act: -0.0000

Data Index: 1383472 (Python Code)

Max Activating Token Index: 540