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

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

Neuron 5730 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: 0.8952. Min Range: -0.8952

Max Act: 0.8952. Min Act: -0.0000

Data Index: 1093363 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.7839. Min Act: -0.0000

Data Index: 1168781 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.8298. Min Act: -0.0000

Data Index: 1222218 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.7997. Min Act: -0.0000

Data Index: 789585 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.8533. Min Act: -0.0000

Data Index: 185557 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.7934. Min Act: -0.0000

Data Index: 255761 (C4 (Web Text))

Max Activating Token Index: 833

Text #6

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.7404. Min Act: -0.0000

Data Index: 1281482 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.7613. Min Act: -0.0000

Data Index: 1229827 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.7262. Min Act: -0.0000

Data Index: 569716 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.7032. Min Act: -0.0000

Data Index: 1364198 (Python Code)

Max Activating Token Index: 403

Text #10

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.6758. Min Act: -0.0000

Data Index: 586258 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.6885. Min Act: -0.0000

Data Index: 1071561 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.6822. Min Act: -0.0000

Data Index: 429926 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.6416. Min Act: -0.0000

Data Index: 152901 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.6554. Min Act: -0.0000

Data Index: 507046 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.6550. Min Act: -0.0000

Data Index: 379152 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.6474. Min Act: 0.0002

Data Index: 628546 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.6461. Min Act: -0.0000

Data Index: 268702 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.6236. Min Act: -0.0000

Data Index: 737561 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.6606. Min Act: -0.0000

Data Index: 313003 (C4 (Web Text))

Max Activating Token Index: 460