Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3398 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0053. Min Act: -0.0003

Data Index: 486987 (C4 (Web Text))

Max Activating Token Index: 321

Text #1

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0053. Min Act: -0.0003

Data Index: 1218562 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0051. Min Act: -0.0003

Data Index: 458032 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0050. Min Act: -0.0003

Data Index: 275206 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0003

Data Index: 1273414 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0044. Min Act: -0.0003

Data Index: 78754 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0046. Min Act: -0.0003

Data Index: 606977 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0041. Min Act: -0.0002

Data Index: 859277 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0043. Min Act: -0.0003

Data Index: 806534 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0043. Min Act: -0.0003

Data Index: 443097 (C4 (Web Text))

Max Activating Token Index: 256

Text #10

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0042. Min Act: -0.0003

Data Index: 1052356 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0042. Min Act: -0.0003

Data Index: 848032 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0041. Min Act: -0.0003

Data Index: 14603 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0041. Min Act: -0.0003

Data Index: 189055 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0041. Min Act: -0.0003

Data Index: 1359214 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0039. Min Act: -0.0003

Data Index: 1200855 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0040. Min Act: -0.0003

Data Index: 329635 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0038. Min Act: -0.0003

Data Index: 451854 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0040. Min Act: -0.0003

Data Index: 1025345 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0040. Min Act: -0.0003

Data Index: 1006705 (C4 (Web Text))

Max Activating Token Index: 207