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

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

Neuron 3479 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.4458. Min Act: -0.0001

Data Index: 1360592 (Python Code)

Max Activating Token Index: 10

Text #1

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3815. Min Act: -0.0001

Data Index: 1445634 (Python Code)

Max Activating Token Index: 625

Text #2

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3599. Min Act: -0.0000

Data Index: 1440418 (Python Code)

Max Activating Token Index: 119

Text #3

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3427. Min Act: -0.0001

Data Index: 1542151 (Python Code)

Max Activating Token Index: 616

Text #4

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3007. Min Act: -0.0001

Data Index: 1431530 (Python Code)

Max Activating Token Index: 176

Text #5

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3087. Min Act: -0.0001

Data Index: 1631864 (Python Code)

Max Activating Token Index: 309

Text #6

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3166. Min Act: -0.0001

Data Index: 1462930 (Python Code)

Max Activating Token Index: 164

Text #7

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3255. Min Act: -0.0001

Data Index: 1401197 (Python Code)

Max Activating Token Index: 112

Text #8

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3042. Min Act: -0.0001

Data Index: 1556761 (Python Code)

Max Activating Token Index: 652

Text #9

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.2894. Min Act: -0.0001

Data Index: 1499290 (Python Code)

Max Activating Token Index: 583

Text #10

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.2889. Min Act: -0.0001

Data Index: 1560453 (Python Code)

Max Activating Token Index: 664

Text #11

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3060. Min Act: -0.0001

Data Index: 1582871 (Python Code)

Max Activating Token Index: 242

Text #12

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3037. Min Act: -0.0001

Data Index: 1436790 (Python Code)

Max Activating Token Index: 292

Text #13

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.2936. Min Act: -0.0000

Data Index: 1605962 (Python Code)

Max Activating Token Index: 171

Text #14

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.2800. Min Act: -0.0001

Data Index: 1570245 (Python Code)

Max Activating Token Index: 1013

Text #15

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.2992. Min Act: -0.0000

Data Index: 1348019 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.2991. Min Act: -0.0001

Data Index: 1482869 (Python Code)

Max Activating Token Index: 487

Text #17

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.2679. Min Act: -0.0001

Data Index: 1396152 (Python Code)

Max Activating Token Index: 49

Text #18

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.2848. Min Act: -0.0000

Data Index: 1488379 (Python Code)

Max Activating Token Index: 245

Text #19

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.2742. Min Act: -0.0001

Data Index: 1597769 (Python Code)

Max Activating Token Index: 740