Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 562 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0079. Min Act: -0.0006

Data Index: 1266626 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0077. Min Act: -0.0006

Data Index: 1261080 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0072. Min Act: -0.0006

Data Index: 659047 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0069. Min Act: -0.0006

Data Index: 811031 (C4 (Web Text))

Max Activating Token Index: 988

Text #4

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0066. Min Act: -0.0006

Data Index: 88760 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0062. Min Act: -0.0006

Data Index: 1092943 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0065. Min Act: -0.0006

Data Index: 1349971 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0065. Min Act: -0.0006

Data Index: 733323 (C4 (Web Text))

Max Activating Token Index: 884

Text #8

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0063. Min Act: -0.0006

Data Index: 1097228 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0060. Min Act: -0.0006

Data Index: 384428 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0060. Min Act: -0.0006

Data Index: 1191265 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0054. Min Act: -0.0006

Data Index: 791668 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0054. Min Act: -0.0006

Data Index: 438685 (C4 (Web Text))

Max Activating Token Index: 471

Text #13

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0058. Min Act: -0.0006

Data Index: 1270641 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0054. Min Act: -0.0006

Data Index: 1242344 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0055. Min Act: -0.0006

Data Index: 22494 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0056. Min Act: -0.0006

Data Index: 680316 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0053. Min Act: -0.0006

Data Index: 593523 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0053. Min Act: -0.0006

Data Index: 851561 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0053. Min Act: -0.0006

Data Index: 931391 (C4 (Web Text))

Max Activating Token Index: 496