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

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

Neuron 320 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: 0.0050. Min Range: -0.0050

Max Act: 0.0050. Min Act: -0.0006

Data Index: 390958 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0047. Min Act: -0.0006

Data Index: 1119252 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0045. Min Act: -0.0006

Data Index: 302938 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0044. Min Act: -0.0005

Data Index: 712913 (C4 (Web Text))

Max Activating Token Index: 623

Text #4

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0044. Min Act: -0.0006

Data Index: 926125 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0043. Min Act: -0.0006

Data Index: 993015 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0043. Min Act: -0.0006

Data Index: 257667 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0042. Min Act: -0.0005

Data Index: 1136825 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0042. Min Act: -0.0006

Data Index: 792986 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0042. Min Act: -0.0006

Data Index: 338769 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0041. Min Act: -0.0006

Data Index: 325566 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0042. Min Act: -0.0006

Data Index: 1020492 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0041. Min Act: -0.0006

Data Index: 25469 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0041. Min Act: -0.0006

Data Index: 1251653 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0041. Min Act: -0.0006

Data Index: 256381 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0041. Min Act: -0.0006

Data Index: 760678 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0042. Min Act: -0.0006

Data Index: 410830 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0041. Min Act: -0.0006

Data Index: 245979 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0041. Min Act: -0.0005

Data Index: 1325153 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0041. Min Act: -0.0005

Data Index: 346545 (C4 (Web Text))

Max Activating Token Index: 629