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

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

Neuron 2745 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1361. Min Range: -1.1361

Max Act: 1.1361. Min Act: 0.0002

Data Index: 1115757 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.9686. Min Act: 0.0000

Data Index: 758286 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.8967. Min Act: -0.0000

Data Index: 667949 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.9130. Min Act: -0.0000

Data Index: 31479 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.9083. Min Act: 0.0000

Data Index: 345602 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.9165. Min Act: 0.0000

Data Index: 243675 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.8608. Min Act: -0.0000

Data Index: 948155 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.8328. Min Act: -0.0000

Data Index: 117678 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.8277. Min Act: -0.0000

Data Index: 423714 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.8055. Min Act: 0.0000

Data Index: 1249659 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.7899. Min Act: 0.0002

Data Index: 1252346 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.7788. Min Act: 0.0002

Data Index: 1117757 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.7830. Min Act: -0.0000

Data Index: 556375 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.7887. Min Act: -0.0000

Data Index: 1073297 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.8106. Min Act: -0.0000

Data Index: 896499 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.7168. Min Act: -0.0000

Data Index: 1114200 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.7129. Min Act: -0.0000

Data Index: 170348 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.7506. Min Act: -0.0000

Data Index: 1620604 (Python Code)

Max Activating Token Index: 249

Text #18

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.7414. Min Act: -0.0000

Data Index: 92585 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 1.1361. Min Range: -1.1361

Max Act: 0.7543. Min Act: -0.0000

Data Index: 1191658 (C4 (Web Text))

Max Activating Token Index: 804