Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4769 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.5090. Min Act: -0.0000

Data Index: 348883 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.5024. Min Act: -0.0000

Data Index: 1136194 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.4372. Min Act: -0.0000

Data Index: 738053 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.3984. Min Act: -0.0000

Data Index: 834732 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.3858. Min Act: -0.0000

Data Index: 687394 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.3810. Min Act: -0.0000

Data Index: 365289 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.3981. Min Act: -0.0000

Data Index: 97076 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.4131. Min Act: -0.0000

Data Index: 503739 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.3713. Min Act: -0.0000

Data Index: 536920 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.3459. Min Act: -0.0000

Data Index: 1127692 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.3807. Min Act: -0.0000

Data Index: 596713 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.3423. Min Act: -0.0000

Data Index: 246901 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.3376. Min Act: -0.0000

Data Index: 583166 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.3247. Min Act: -0.0000

Data Index: 1038361 (C4 (Web Text))

Max Activating Token Index: 520

Text #14

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.3353. Min Act: -0.0000

Data Index: 1078077 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.3339. Min Act: -0.0000

Data Index: 1356034 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.3348. Min Act: -0.0000

Data Index: 958344 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.3427. Min Act: -0.0000

Data Index: 80635 (C4 (Web Text))

Max Activating Token Index: 462

Text #18

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.3319. Min Act: -0.0000

Data Index: 1219575 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.3187. Min Act: -0.0000

Data Index: 1263399 (C4 (Web Text))

Max Activating Token Index: 430