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

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

Neuron 2014 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0053. Min Act: -0.0006

Data Index: 266631 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0053. Min Act: -0.0006

Data Index: 1053728 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0044. Min Act: -0.0006

Data Index: 336473 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0050. Min Act: -0.0006

Data Index: 524257 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0051. Min Act: -0.0006

Data Index: 729983 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0047. Min Act: -0.0006

Data Index: 614367 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0052. Min Act: -0.0006

Data Index: 776703 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0046. Min Act: -0.0006

Data Index: 763089 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0046. Min Act: -0.0006

Data Index: 178839 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0047. Min Act: -0.0007

Data Index: 1141377 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0047. Min Act: -0.0006

Data Index: 800285 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0044. Min Act: -0.0006

Data Index: 1282693 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0041. Min Act: -0.0006

Data Index: 2624 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0044. Min Act: -0.0006

Data Index: 1152009 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0039. Min Act: -0.0006

Data Index: 819454 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0046. Min Act: -0.0006

Data Index: 1028991 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0041. Min Act: -0.0006

Data Index: 150568 (C4 (Web Text))

Max Activating Token Index: 277

Text #17

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0043. Min Act: -0.0006

Data Index: 730134 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0044. Min Act: -0.0006

Data Index: 96529 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0042. Min Act: -0.0006

Data Index: 357613 (C4 (Web Text))

Max Activating Token Index: 955