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

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

Neuron 1225 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0125. Min Range: -1.0125

Max Act: 1.0125. Min Act: -0.0001

Data Index: 633324 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.9582. Min Act: -0.0001

Data Index: 1175746 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.9487. Min Act: -0.0001

Data Index: 260746 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.8006. Min Act: -0.0001

Data Index: 1461404 (Python Code)

Max Activating Token Index: 910

Text #4

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.9167. Min Act: -0.0001

Data Index: 1454608 (Python Code)

Max Activating Token Index: 316

Text #5

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.8839. Min Act: -0.0001

Data Index: 611292 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.8276. Min Act: -0.0001

Data Index: 1198568 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.8112. Min Act: -0.0001

Data Index: 1504305 (Python Code)

Max Activating Token Index: 660

Text #8

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.8051. Min Act: -0.0001

Data Index: 1414536 (Python Code)

Max Activating Token Index: 589

Text #9

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.7596. Min Act: -0.0001

Data Index: 1397081 (Python Code)

Max Activating Token Index: 302

Text #10

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.7454. Min Act: -0.0001

Data Index: 1592957 (Python Code)

Max Activating Token Index: 837

Text #11

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.7911. Min Act: -0.0001

Data Index: 339033 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.7432. Min Act: -0.0001

Data Index: 1534316 (Python Code)

Max Activating Token Index: 453

Text #13

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.7490. Min Act: -0.0001

Data Index: 898969 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.6871. Min Act: -0.0001

Data Index: 1528123 (Python Code)

Max Activating Token Index: 199

Text #15

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.7171. Min Act: -0.0001

Data Index: 984645 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.7049. Min Act: -0.0001

Data Index: 1033998 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.7269. Min Act: -0.0001

Data Index: 1547435 (Python Code)

Max Activating Token Index: 461

Text #18

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.6905. Min Act: -0.0001

Data Index: 1283168 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.6842. Min Act: -0.0001

Data Index: 1637591 (Python Code)

Max Activating Token Index: 895