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

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

Neuron 3760 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: 1.3089. Min Range: -1.3089

Max Act: 1.3089. Min Act: -0.0001

Data Index: 1533152 (Python Code)

Max Activating Token Index: 1013

Text #1

Max Range: 1.3089. Min Range: -1.3089

Max Act: 1.2207. Min Act: -0.0001

Data Index: 1365512 (Python Code)

Max Activating Token Index: 397

Text #2

Max Range: 1.3089. Min Range: -1.3089

Max Act: 1.2320. Min Act: -0.0001

Data Index: 1408774 (Python Code)

Max Activating Token Index: 830

Text #3

Max Range: 1.3089. Min Range: -1.3089

Max Act: 1.2644. Min Act: -0.0001

Data Index: 1615703 (Python Code)

Max Activating Token Index: 455

Text #4

Max Range: 1.3089. Min Range: -1.3089

Max Act: 1.1364. Min Act: -0.0000

Data Index: 1368419 (Python Code)

Max Activating Token Index: 419

Text #5

Max Range: 1.3089. Min Range: -1.3089

Max Act: 1.2172. Min Act: -0.0001

Data Index: 1470613 (Python Code)

Max Activating Token Index: 674

Text #6

Max Range: 1.3089. Min Range: -1.3089

Max Act: 1.1190. Min Act: -0.0001

Data Index: 1486592 (Python Code)

Max Activating Token Index: 755

Text #7

Max Range: 1.3089. Min Range: -1.3089

Max Act: 1.1018. Min Act: -0.0001

Data Index: 1474234 (Python Code)

Max Activating Token Index: 224

Text #8

Max Range: 1.3089. Min Range: -1.3089

Max Act: 1.1287. Min Act: -0.0001

Data Index: 1415648 (Python Code)

Max Activating Token Index: 535

Text #9

Max Range: 1.3089. Min Range: -1.3089

Max Act: 1.1232. Min Act: -0.0001

Data Index: 1517982 (Python Code)

Max Activating Token Index: 537

Text #10

Max Range: 1.3089. Min Range: -1.3089

Max Act: 1.0113. Min Act: -0.0000

Data Index: 1372397 (Python Code)

Max Activating Token Index: 960

Text #11

Max Range: 1.3089. Min Range: -1.3089

Max Act: 1.1960. Min Act: -0.0001

Data Index: 1651872 (Python Code)

Max Activating Token Index: 669

Text #12

Max Range: 1.3089. Min Range: -1.3089

Max Act: 0.9731. Min Act: -0.0001

Data Index: 1507332 (Python Code)

Max Activating Token Index: 793

Text #13

Max Range: 1.3089. Min Range: -1.3089

Max Act: 1.0655. Min Act: -0.0001

Data Index: 1487479 (Python Code)

Max Activating Token Index: 360

Text #14

Max Range: 1.3089. Min Range: -1.3089

Max Act: 1.0977. Min Act: -0.0001

Data Index: 1524235 (Python Code)

Max Activating Token Index: 578

Text #15

Max Range: 1.3089. Min Range: -1.3089

Max Act: 1.0457. Min Act: -0.0001

Data Index: 1464572 (Python Code)

Max Activating Token Index: 302

Text #16

Max Range: 1.3089. Min Range: -1.3089

Max Act: 0.9474. Min Act: -0.0001

Data Index: 1618107 (Python Code)

Max Activating Token Index: 367

Text #17

Max Range: 1.3089. Min Range: -1.3089

Max Act: 1.0719. Min Act: -0.0001

Data Index: 1590667 (Python Code)

Max Activating Token Index: 278

Text #18

Max Range: 1.3089. Min Range: -1.3089

Max Act: 1.0600. Min Act: -0.0000

Data Index: 1474035 (Python Code)

Max Activating Token Index: 197

Text #19

Max Range: 1.3089. Min Range: -1.3089

Max Act: 1.0316. Min Act: -0.0001

Data Index: 1400115 (Python Code)

Max Activating Token Index: 332