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

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

Neuron 750 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: 0.0043. Min Range: -0.0043

Max Act: 0.0043. Min Act: -0.0005

Data Index: 1400021 (Python Code)

Max Activating Token Index: 309

Text #1

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0041. Min Act: -0.0006

Data Index: 452538 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0038. Min Act: -0.0006

Data Index: 159230 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0039. Min Act: -0.0005

Data Index: 622797 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0039. Min Act: -0.0006

Data Index: 255928 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0038. Min Act: -0.0006

Data Index: 289849 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0036. Min Act: -0.0006

Data Index: 964626 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0035. Min Act: -0.0006

Data Index: 122559 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0036. Min Act: -0.0005

Data Index: 640302 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0035. Min Act: -0.0006

Data Index: 88647 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0034. Min Act: -0.0006

Data Index: 310275 (C4 (Web Text))

Max Activating Token Index: 752

Text #11

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0033. Min Act: -0.0005

Data Index: 157752 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0035. Min Act: -0.0006

Data Index: 1357183 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0035. Min Act: -0.0006

Data Index: 317961 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0033. Min Act: -0.0005

Data Index: 761383 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0034. Min Act: -0.0006

Data Index: 332015 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0034. Min Act: -0.0006

Data Index: 676869 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0033. Min Act: -0.0006

Data Index: 800369 (C4 (Web Text))

Max Activating Token Index: 8

Text #18

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0032. Min Act: -0.0006

Data Index: 712142 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0033. Min Act: -0.0006

Data Index: 365047 (C4 (Web Text))

Max Activating Token Index: 984