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

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

Neuron 542 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1792. Min Act: -0.0001

Data Index: 21263 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1597. Min Act: -0.0001

Data Index: 276279 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1281. Min Act: -0.0001

Data Index: 882104 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1354. Min Act: -0.0001

Data Index: 21020 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1317. Min Act: -0.0001

Data Index: 105160 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1276. Min Act: -0.0001

Data Index: 364679 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1194. Min Act: -0.0001

Data Index: 603031 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1011. Min Act: -0.0001

Data Index: 410924 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.0961. Min Act: -0.0001

Data Index: 988381 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1146. Min Act: -0.0001

Data Index: 1337169 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1155. Min Act: -0.0001

Data Index: 821111 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1230. Min Act: -0.0001

Data Index: 1347297 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1145. Min Act: -0.0001

Data Index: 234384 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1138. Min Act: -0.0001

Data Index: 106537 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1212. Min Act: -0.0001

Data Index: 1230020 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1181. Min Act: -0.0001

Data Index: 573802 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1105. Min Act: -0.0001

Data Index: 27253 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1129. Min Act: -0.0001

Data Index: 1226644 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1002. Min Act: -0.0001

Data Index: 565042 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.0915. Min Act: -0.0001

Data Index: 803531 (C4 (Web Text))

Max Activating Token Index: 584