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

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

Neuron 685 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0068. Min Act: -0.0006

Data Index: 599004 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0067. Min Act: -0.0006

Data Index: 518066 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0066. Min Act: -0.0006

Data Index: 1146460 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0064. Min Act: -0.0006

Data Index: 924134 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0064. Min Act: -0.0006

Data Index: 601912 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0063. Min Act: -0.0006

Data Index: 70843 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0063. Min Act: -0.0006

Data Index: 323258 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0062. Min Act: -0.0006

Data Index: 923703 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0062. Min Act: -0.0005

Data Index: 956202 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0062. Min Act: -0.0006

Data Index: 753952 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0062. Min Act: -0.0006

Data Index: 1049017 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0061. Min Act: -0.0006

Data Index: 789360 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0061. Min Act: -0.0006

Data Index: 892379 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0061. Min Act: -0.0006

Data Index: 971169 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0061. Min Act: -0.0006

Data Index: 1078846 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0061. Min Act: -0.0006

Data Index: 677962 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0060. Min Act: -0.0006

Data Index: 811408 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0060. Min Act: -0.0006

Data Index: 488222 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0060. Min Act: -0.0006

Data Index: 557613 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0060. Min Act: -0.0006

Data Index: 387045 (C4 (Web Text))

Max Activating Token Index: 572