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

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

Neuron 1095 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: 0.1187. Min Range: -0.1187

Max Act: 0.1187. Min Act: -0.0003

Data Index: 1130508 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1143. Min Act: -0.0003

Data Index: 591938 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1165. Min Act: -0.0003

Data Index: 1149780 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1049. Min Act: -0.0003

Data Index: 954595 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1070. Min Act: -0.0003

Data Index: 197721 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0959. Min Act: -0.0003

Data Index: 559231 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0981. Min Act: -0.0003

Data Index: 81884 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0977. Min Act: -0.0003

Data Index: 882519 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1020. Min Act: -0.0003

Data Index: 1200629 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1041. Min Act: -0.0003

Data Index: 594986 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0893. Min Act: -0.0003

Data Index: 249478 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0925. Min Act: -0.0003

Data Index: 169638 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0927. Min Act: -0.0003

Data Index: 240808 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0956. Min Act: -0.0003

Data Index: 503632 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0957. Min Act: -0.0003

Data Index: 961432 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0946. Min Act: -0.0003

Data Index: 1092199 (C4 (Web Text))

Max Activating Token Index: 754

Text #16

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0874. Min Act: -0.0003

Data Index: 1107987 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0846. Min Act: -0.0003

Data Index: 555134 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0872. Min Act: -0.0003

Data Index: 554620 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0906. Min Act: -0.0003

Data Index: 807251 (C4 (Web Text))

Max Activating Token Index: 779