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

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

Neuron 1436 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1252. Min Act: -0.0001

Data Index: 446384 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0890. Min Act: -0.0001

Data Index: 387538 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0592. Min Act: -0.0001

Data Index: 909630 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0620. Min Act: -0.0001

Data Index: 707816 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0633. Min Act: -0.0001

Data Index: 1517958 (Python Code)

Max Activating Token Index: 980

Text #5

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0720. Min Act: -0.0001

Data Index: 184285 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0583. Min Act: -0.0001

Data Index: 1029523 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0569. Min Act: -0.0001

Data Index: 445120 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0544. Min Act: -0.0001

Data Index: 554399 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0477. Min Act: -0.0001

Data Index: 1088984 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0472. Min Act: -0.0001

Data Index: 1316586 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0575. Min Act: -0.0001

Data Index: 826259 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0502. Min Act: -0.0001

Data Index: 964900 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0500. Min Act: -0.0001

Data Index: 1569001 (Python Code)

Max Activating Token Index: 396

Text #14

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0470. Min Act: -0.0001

Data Index: 982210 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0482. Min Act: -0.0001

Data Index: 962073 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0468. Min Act: -0.0001

Data Index: 201358 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0533. Min Act: -0.0001

Data Index: 868364 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0455. Min Act: -0.0001

Data Index: 760010 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0445. Min Act: -0.0001

Data Index: 1569109 (Python Code)

Max Activating Token Index: 542