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

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

Neuron 838 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1163. Min Range: -1.1163

Max Act: 1.1163. Min Act: -0.0001

Data Index: 96536 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 1.1163. Min Range: -1.1163

Max Act: 1.0604. Min Act: -0.0001

Data Index: 763119 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 1.1163. Min Range: -1.1163

Max Act: 1.0642. Min Act: -0.0001

Data Index: 1268444 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 1.1163. Min Range: -1.1163

Max Act: 0.9871. Min Act: -0.0001

Data Index: 1171783 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 1.1163. Min Range: -1.1163

Max Act: 0.8907. Min Act: -0.0001

Data Index: 1279130 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 1.1163. Min Range: -1.1163

Max Act: 0.9471. Min Act: -0.0001

Data Index: 432394 (C4 (Web Text))

Max Activating Token Index: 290

Text #6

Max Range: 1.1163. Min Range: -1.1163

Max Act: 0.8998. Min Act: -0.0001

Data Index: 756813 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 1.1163. Min Range: -1.1163

Max Act: 0.9008. Min Act: -0.0001

Data Index: 223097 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 1.1163. Min Range: -1.1163

Max Act: 0.8834. Min Act: -0.0001

Data Index: 199071 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 1.1163. Min Range: -1.1163

Max Act: 0.8815. Min Act: -0.0001

Data Index: 1077528 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 1.1163. Min Range: -1.1163

Max Act: 0.9034. Min Act: -0.0001

Data Index: 522352 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 1.1163. Min Range: -1.1163

Max Act: 0.9060. Min Act: -0.0001

Data Index: 348691 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 1.1163. Min Range: -1.1163

Max Act: 0.8585. Min Act: -0.0001

Data Index: 941024 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 1.1163. Min Range: -1.1163

Max Act: 0.8332. Min Act: -0.0001

Data Index: 82672 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 1.1163. Min Range: -1.1163

Max Act: 0.8125. Min Act: -0.0001

Data Index: 363003 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 1.1163. Min Range: -1.1163

Max Act: 0.9046. Min Act: -0.0001

Data Index: 997388 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 1.1163. Min Range: -1.1163

Max Act: 0.9082. Min Act: -0.0001

Data Index: 129206 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 1.1163. Min Range: -1.1163

Max Act: 0.9074. Min Act: -0.0001

Data Index: 1013175 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 1.1163. Min Range: -1.1163

Max Act: 0.9073. Min Act: -0.0001

Data Index: 854181 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 1.1163. Min Range: -1.1163

Max Act: 0.8383. Min Act: -0.0001

Data Index: 851569 (C4 (Web Text))

Max Activating Token Index: 379