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

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

Neuron 1805 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: 0.1208. Min Range: -0.1208

Max Act: 0.1208. Min Act: -0.0001

Data Index: 1509331 (Python Code)

Max Activating Token Index: 857

Text #1

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.1157. Min Act: -0.0001

Data Index: 1110463 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.1110. Min Act: -0.0001

Data Index: 1389603 (Python Code)

Max Activating Token Index: 38

Text #3

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.1093. Min Act: -0.0001

Data Index: 1436562 (Python Code)

Max Activating Token Index: 124

Text #4

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.1021. Min Act: -0.0001

Data Index: 11756 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0948. Min Act: -0.0001

Data Index: 1617180 (Python Code)

Max Activating Token Index: 564

Text #6

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0973. Min Act: -0.0001

Data Index: 643174 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0935. Min Act: -0.0001

Data Index: 1381921 (Python Code)

Max Activating Token Index: 72

Text #8

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0928. Min Act: -0.0001

Data Index: 1578015 (Python Code)

Max Activating Token Index: 643

Text #9

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0911. Min Act: -0.0001

Data Index: 1549109 (Python Code)

Max Activating Token Index: 38

Text #10

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0851. Min Act: -0.0001

Data Index: 1586250 (Python Code)

Max Activating Token Index: 415

Text #11

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0980. Min Act: -0.0001

Data Index: 904550 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0935. Min Act: -0.0001

Data Index: 77563 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0964. Min Act: -0.0001

Data Index: 815405 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0969. Min Act: -0.0001

Data Index: 1525397 (Python Code)

Max Activating Token Index: 52

Text #15

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0972. Min Act: -0.0001

Data Index: 1591098 (Python Code)

Max Activating Token Index: 735

Text #16

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.1071. Min Act: -0.0001

Data Index: 1588661 (Python Code)

Max Activating Token Index: 596

Text #17

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0893. Min Act: -0.0001

Data Index: 1522826 (Python Code)

Max Activating Token Index: 160

Text #18

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0913. Min Act: -0.0001

Data Index: 1232962 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0914. Min Act: -0.0001

Data Index: 557639 (C4 (Web Text))

Max Activating Token Index: 44