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

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

Neuron 1260 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.3467. Min Act: -0.0001

Data Index: 1637991 (Python Code)

Max Activating Token Index: 568

Text #1

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.2442. Min Act: -0.0001

Data Index: 1646853 (Python Code)

Max Activating Token Index: 152

Text #2

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.1696. Min Act: -0.0001

Data Index: 1471021 (Python Code)

Max Activating Token Index: 172

Text #3

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.1141. Min Act: -0.0001

Data Index: 1557126 (Python Code)

Max Activating Token Index: 653

Text #4

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.1524. Min Act: -0.0001

Data Index: 1424001 (Python Code)

Max Activating Token Index: 700

Text #5

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.1101. Min Act: -0.0001

Data Index: 1569052 (Python Code)

Max Activating Token Index: 122

Text #6

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.1176. Min Act: -0.0001

Data Index: 1649562 (Python Code)

Max Activating Token Index: 388

Text #7

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.1261. Min Act: -0.0001

Data Index: 1643162 (Python Code)

Max Activating Token Index: 928

Text #8

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.1119. Min Act: -0.0001

Data Index: 1564720 (Python Code)

Max Activating Token Index: 838

Text #9

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.0711. Min Act: -0.0001

Data Index: 1540460 (Python Code)

Max Activating Token Index: 457

Text #10

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.0661. Min Act: -0.0001

Data Index: 1633548 (Python Code)

Max Activating Token Index: 32

Text #11

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.1448. Min Act: -0.0001

Data Index: 1582132 (Python Code)

Max Activating Token Index: 893

Text #12

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.0695. Min Act: -0.0001

Data Index: 1579734 (Python Code)

Max Activating Token Index: 255

Text #13

Max Range: 1.3467. Min Range: -1.3467

Max Act: 0.9946. Min Act: -0.0001

Data Index: 1498051 (Python Code)

Max Activating Token Index: 784

Text #14

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.0258. Min Act: -0.0001

Data Index: 1473865 (Python Code)

Max Activating Token Index: 240

Text #15

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.0099. Min Act: -0.0001

Data Index: 1531334 (Python Code)

Max Activating Token Index: 532

Text #16

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.0533. Min Act: -0.0001

Data Index: 1534571 (Python Code)

Max Activating Token Index: 501

Text #17

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.0361. Min Act: -0.0001

Data Index: 1464928 (Python Code)

Max Activating Token Index: 231

Text #18

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.0613. Min Act: -0.0001

Data Index: 1373435 (Python Code)

Max Activating Token Index: 406

Text #19

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.0892. Min Act: -0.0001

Data Index: 1638331 (Python Code)

Max Activating Token Index: 183