Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2522 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1157. Min Act: -0.0001

Data Index: 26964 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1061. Min Act: -0.0001

Data Index: 30485 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0982. Min Act: -0.0001

Data Index: 806587 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1046. Min Act: -0.0001

Data Index: 631962 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1099. Min Act: -0.0001

Data Index: 712742 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0786. Min Act: -0.0001

Data Index: 527628 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0936. Min Act: -0.0001

Data Index: 1261911 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0960. Min Act: -0.0001

Data Index: 656134 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0899. Min Act: -0.0001

Data Index: 1138917 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0934. Min Act: -0.0001

Data Index: 284753 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0917. Min Act: -0.0001

Data Index: 550994 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0937. Min Act: -0.0001

Data Index: 148262 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0904. Min Act: -0.0001

Data Index: 717741 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0866. Min Act: -0.0001

Data Index: 934366 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0863. Min Act: -0.0001

Data Index: 1243964 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0887. Min Act: -0.0001

Data Index: 1224535 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0969. Min Act: -0.0001

Data Index: 511348 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0890. Min Act: -0.0001

Data Index: 282261 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0843. Min Act: -0.0001

Data Index: 1154414 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0944. Min Act: -0.0001

Data Index: 808102 (C4 (Web Text))

Max Activating Token Index: 264