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

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

Neuron 1689 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0074. Min Act: -0.0003

Data Index: 903600 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0051. Min Act: -0.0002

Data Index: 675788 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0041. Min Act: -0.0002

Data Index: 588699 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0042. Min Act: -0.0002

Data Index: 306981 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0040. Min Act: -0.0002

Data Index: 966167 (C4 (Web Text))

Max Activating Token Index: 352

Text #5

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0041. Min Act: -0.0003

Data Index: 132874 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0039. Min Act: -0.0002

Data Index: 1302477 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0036. Min Act: -0.0002

Data Index: 815602 (C4 (Web Text))

Max Activating Token Index: 755

Text #8

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0036. Min Act: -0.0002

Data Index: 1149820 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0036. Min Act: -0.0002

Data Index: 506377 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0035. Min Act: -0.0002

Data Index: 779253 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0033. Min Act: -0.0003

Data Index: 238374 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0034. Min Act: -0.0002

Data Index: 748251 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0034. Min Act: -0.0002

Data Index: 1544308 (Python Code)

Max Activating Token Index: 329

Text #14

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0033. Min Act: -0.0003

Data Index: 750605 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0035. Min Act: -0.0002

Data Index: 107269 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0033. Min Act: -0.0002

Data Index: 177312 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0035. Min Act: -0.0002

Data Index: 271413 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0035. Min Act: -0.0002

Data Index: 1207690 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0033. Min Act: -0.0003

Data Index: 873046 (C4 (Web Text))

Max Activating Token Index: 197