Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3896 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1274. Min Act: -0.0001

Data Index: 553365 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1148. Min Act: -0.0001

Data Index: 949236 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1069. Min Act: -0.0001

Data Index: 686179 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1160. Min Act: -0.0001

Data Index: 963184 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1104. Min Act: -0.0001

Data Index: 342801 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1066. Min Act: -0.0001

Data Index: 861448 (C4 (Web Text))

Max Activating Token Index: 449

Text #6

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1068. Min Act: -0.0001

Data Index: 309418 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1064. Min Act: -0.0001

Data Index: 397121 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1129. Min Act: -0.0001

Data Index: 1310277 (C4 (Web Text))

Max Activating Token Index: 963

Text #9

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1040. Min Act: -0.0001

Data Index: 163787 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1077. Min Act: -0.0001

Data Index: 740562 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1020. Min Act: -0.0001

Data Index: 854508 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1009. Min Act: -0.0001

Data Index: 133172 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.0988. Min Act: -0.0001

Data Index: 1062554 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1023. Min Act: -0.0001

Data Index: 722451 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.0995. Min Act: -0.0001

Data Index: 966528 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.0947. Min Act: -0.0001

Data Index: 203300 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.0953. Min Act: -0.0001

Data Index: 1314758 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.0956. Min Act: -0.0001

Data Index: 73296 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.0990. Min Act: -0.0001

Data Index: 876702 (C4 (Web Text))

Max Activating Token Index: 612