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

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

Neuron 4136 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: 3.7735. Min Range: -3.7735

Max Act: 3.7712. Min Act: -0.0000

Data Index: 1473372 (Python Code)

Max Activating Token Index: 77

Text #1

Max Range: 3.7735. Min Range: -3.7735

Max Act: 3.7735. Min Act: -0.0000

Data Index: 1441863 (Python Code)

Max Activating Token Index: 148

Text #2

Max Range: 3.7735. Min Range: -3.7735

Max Act: 3.4370. Min Act: -0.0000

Data Index: 1482312 (Python Code)

Max Activating Token Index: 1019

Text #3

Max Range: 3.7735. Min Range: -3.7735

Max Act: 3.4061. Min Act: -0.0000

Data Index: 1483716 (Python Code)

Max Activating Token Index: 267

Text #4

Max Range: 3.7735. Min Range: -3.7735

Max Act: 3.3374. Min Act: -0.0000

Data Index: 1471592 (Python Code)

Max Activating Token Index: 626

Text #5

Max Range: 3.7735. Min Range: -3.7735

Max Act: 3.3216. Min Act: -0.0000

Data Index: 1428019 (Python Code)

Max Activating Token Index: 351

Text #6

Max Range: 3.7735. Min Range: -3.7735

Max Act: 3.6489. Min Act: -0.0000

Data Index: 1396992 (Python Code)

Max Activating Token Index: 624

Text #7

Max Range: 3.7735. Min Range: -3.7735

Max Act: 3.5892. Min Act: -0.0000

Data Index: 1579023 (Python Code)

Max Activating Token Index: 271

Text #8

Max Range: 3.7735. Min Range: -3.7735

Max Act: 3.2670. Min Act: -0.0000

Data Index: 1451338 (Python Code)

Max Activating Token Index: 609

Text #9

Max Range: 3.7735. Min Range: -3.7735

Max Act: 3.5425. Min Act: -0.0000

Data Index: 1631616 (Python Code)

Max Activating Token Index: 950

Text #10

Max Range: 3.7735. Min Range: -3.7735

Max Act: 3.3271. Min Act: -0.0000

Data Index: 1553735 (Python Code)

Max Activating Token Index: 108

Text #11

Max Range: 3.7735. Min Range: -3.7735

Max Act: 3.3134. Min Act: -0.0000

Data Index: 1631232 (Python Code)

Max Activating Token Index: 85

Text #12

Max Range: 3.7735. Min Range: -3.7735

Max Act: 3.2885. Min Act: -0.0000

Data Index: 1485324 (Python Code)

Max Activating Token Index: 991

Text #13

Max Range: 3.7735. Min Range: -3.7735

Max Act: 3.1304. Min Act: -0.0000

Data Index: 1449691 (Python Code)

Max Activating Token Index: 322

Text #14

Max Range: 3.7735. Min Range: -3.7735

Max Act: 3.2720. Min Act: -0.0000

Data Index: 1654061 (Python Code)

Max Activating Token Index: 165

Text #15

Max Range: 3.7735. Min Range: -3.7735

Max Act: 3.2582. Min Act: -0.0000

Data Index: 1540906 (Python Code)

Max Activating Token Index: 543

Text #16

Max Range: 3.7735. Min Range: -3.7735

Max Act: 3.2400. Min Act: -0.0000

Data Index: 1543975 (Python Code)

Max Activating Token Index: 45

Text #17

Max Range: 3.7735. Min Range: -3.7735

Max Act: 3.1081. Min Act: -0.0000

Data Index: 1603008 (Python Code)

Max Activating Token Index: 503

Text #18

Max Range: 3.7735. Min Range: -3.7735

Max Act: 3.2325. Min Act: -0.0000

Data Index: 1433117 (Python Code)

Max Activating Token Index: 479

Text #19

Max Range: 3.7735. Min Range: -3.7735

Max Act: 3.3575. Min Act: -0.0000

Data Index: 1637270 (Python Code)

Max Activating Token Index: 174