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

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

Neuron 1377 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: 0.1574. Min Range: -0.1574

Max Act: 0.1574. Min Act: -0.0001

Data Index: 469416 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1388. Min Act: -0.0001

Data Index: 877577 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1257. Min Act: -0.0001

Data Index: 65556 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1313. Min Act: -0.0001

Data Index: 946960 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1258. Min Act: -0.0001

Data Index: 458805 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1220. Min Act: -0.0001

Data Index: 217992 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1169. Min Act: -0.0001

Data Index: 1056447 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1147. Min Act: -0.0001

Data Index: 1149064 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1137. Min Act: -0.0001

Data Index: 968434 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1109. Min Act: -0.0001

Data Index: 74505 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1025. Min Act: -0.0001

Data Index: 236239 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1078. Min Act: -0.0001

Data Index: 1218442 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1174. Min Act: -0.0001

Data Index: 997030 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1134. Min Act: -0.0001

Data Index: 1049725 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1104. Min Act: -0.0001

Data Index: 760883 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1119. Min Act: -0.0001

Data Index: 646838 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1146. Min Act: -0.0001

Data Index: 904395 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1191. Min Act: -0.0001

Data Index: 93082 (C4 (Web Text))

Max Activating Token Index: 834

Text #18

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1099. Min Act: -0.0001

Data Index: 365144 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1079. Min Act: -0.0001

Data Index: 26403 (C4 (Web Text))

Max Activating Token Index: 818