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

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

Neuron 1418 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: 0.1474. Min Range: -0.1474

Max Act: 0.1474. Min Act: -0.0001

Data Index: 750961 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1422. Min Act: -0.0001

Data Index: 74198 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1283. Min Act: -0.0001

Data Index: 27910 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1294. Min Act: -0.0001

Data Index: 902839 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1244. Min Act: -0.0001

Data Index: 1130992 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1149. Min Act: -0.0001

Data Index: 741297 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1119. Min Act: -0.0001

Data Index: 1135109 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1143. Min Act: -0.0001

Data Index: 1306445 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1133. Min Act: -0.0001

Data Index: 856213 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1060. Min Act: -0.0001

Data Index: 446964 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1148. Min Act: -0.0001

Data Index: 333884 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1061. Min Act: -0.0001

Data Index: 438702 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1089. Min Act: -0.0001

Data Index: 1236415 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1038. Min Act: -0.0001

Data Index: 449139 (C4 (Web Text))

Max Activating Token Index: 660

Text #14

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.0987. Min Act: -0.0001

Data Index: 989811 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1015. Min Act: -0.0001

Data Index: 1238386 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1037. Min Act: -0.0001

Data Index: 835614 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1110. Min Act: -0.0001

Data Index: 237415 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1027. Min Act: -0.0001

Data Index: 486703 (C4 (Web Text))

Max Activating Token Index: 548

Text #19

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1049. Min Act: -0.0001

Data Index: 507974 (C4 (Web Text))

Max Activating Token Index: 880