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

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

Neuron 17 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1346. Min Act: -0.0003

Data Index: 1093091 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1265. Min Act: -0.0003

Data Index: 1233907 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1296. Min Act: -0.0003

Data Index: 535983 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1066. Min Act: -0.0003

Data Index: 500902 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1329. Min Act: -0.0003

Data Index: 633241 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1231. Min Act: -0.0003

Data Index: 895044 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1182. Min Act: -0.0003

Data Index: 809287 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1206. Min Act: -0.0003

Data Index: 744521 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1199. Min Act: -0.0003

Data Index: 107696 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1236. Min Act: -0.0003

Data Index: 163939 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1156. Min Act: -0.0003

Data Index: 729783 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1183. Min Act: -0.0003

Data Index: 100675 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1008. Min Act: -0.0003

Data Index: 897820 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1113. Min Act: -0.0003

Data Index: 822639 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1157. Min Act: -0.0003

Data Index: 527973 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1113. Min Act: -0.0003

Data Index: 674790 (C4 (Web Text))

Max Activating Token Index: 429

Text #16

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1136. Min Act: -0.0003

Data Index: 727456 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1106. Min Act: -0.0003

Data Index: 606695 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1032. Min Act: -0.0003

Data Index: 1047881 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1130. Min Act: -0.0003

Data Index: 919124 (C4 (Web Text))

Max Activating Token Index: 954