Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1856 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0050. Min Act: -0.0005

Data Index: 2827 (C4 (Web Text))

Max Activating Token Index: 558

Text #1

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0050. Min Act: -0.0005

Data Index: 713389 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0049. Min Act: -0.0005

Data Index: 753982 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0049. Min Act: -0.0005

Data Index: 853888 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0047. Min Act: -0.0005

Data Index: 966324 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0047. Min Act: -0.0005

Data Index: 100164 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0047. Min Act: -0.0005

Data Index: 1013392 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0046. Min Act: -0.0005

Data Index: 276286 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0046. Min Act: -0.0005

Data Index: 614015 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0045. Min Act: -0.0006

Data Index: 392400 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0044. Min Act: -0.0005

Data Index: 491264 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0043. Min Act: -0.0006

Data Index: 407432 (C4 (Web Text))

Max Activating Token Index: 320

Text #12

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0044. Min Act: -0.0005

Data Index: 1050794 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0043. Min Act: -0.0005

Data Index: 551167 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0043. Min Act: -0.0005

Data Index: 378117 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0043. Min Act: -0.0005

Data Index: 107314 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0043. Min Act: -0.0005

Data Index: 872334 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0042. Min Act: -0.0005

Data Index: 1112826 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0043. Min Act: -0.0005

Data Index: 246504 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0042. Min Act: -0.0005

Data Index: 47833 (C4 (Web Text))

Max Activating Token Index: 316