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

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

Neuron 352 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: 0.1330. Min Range: -0.1330

Max Act: 0.1327. Min Act: -0.0001

Data Index: 703698 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1330. Min Act: -0.0001

Data Index: 494471 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1202. Min Act: -0.0001

Data Index: 186076 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1082. Min Act: -0.0001

Data Index: 628683 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1285. Min Act: -0.0001

Data Index: 1291003 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1141. Min Act: -0.0001

Data Index: 990854 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1202. Min Act: -0.0001

Data Index: 1147620 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1129. Min Act: -0.0001

Data Index: 1221116 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1228. Min Act: -0.0001

Data Index: 1197476 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1026. Min Act: -0.0001

Data Index: 914686 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1097. Min Act: -0.0001

Data Index: 506405 (C4 (Web Text))

Max Activating Token Index: 491

Text #11

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1187. Min Act: -0.0001

Data Index: 1265707 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1111. Min Act: -0.0001

Data Index: 344328 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1115. Min Act: -0.0001

Data Index: 488965 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1119. Min Act: -0.0001

Data Index: 1315711 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0996. Min Act: -0.0001

Data Index: 407574 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1105. Min Act: -0.0001

Data Index: 842991 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1076. Min Act: -0.0001

Data Index: 290454 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1200. Min Act: -0.0001

Data Index: 999397 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1110. Min Act: -0.0001

Data Index: 1272935 (C4 (Web Text))

Max Activating Token Index: 358