Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1494 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.5149. Min Range: -0.5149

Max Act: 0.5149. Min Act: -0.0001

Data Index: 707683 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.5149. Min Range: -0.5149

Max Act: 0.4971. Min Act: -0.0001

Data Index: 440298 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 0.5149. Min Range: -0.5149

Max Act: 0.4511. Min Act: -0.0001

Data Index: 169788 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.5149. Min Range: -0.5149

Max Act: 0.4470. Min Act: -0.0001

Data Index: 779627 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 0.5149. Min Range: -0.5149

Max Act: 0.4556. Min Act: -0.0001

Data Index: 283159 (C4 (Web Text))

Max Activating Token Index: 485

Text #5

Max Range: 0.5149. Min Range: -0.5149

Max Act: 0.4278. Min Act: -0.0001

Data Index: 1181435 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 0.5149. Min Range: -0.5149

Max Act: 0.4106. Min Act: -0.0000

Data Index: 1287394 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 0.5149. Min Range: -0.5149

Max Act: 0.4121. Min Act: -0.0000

Data Index: 258122 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 0.5149. Min Range: -0.5149

Max Act: 0.4009. Min Act: -0.0000

Data Index: 691760 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 0.5149. Min Range: -0.5149

Max Act: 0.4166. Min Act: -0.0001

Data Index: 33179 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.5149. Min Range: -0.5149

Max Act: 0.4104. Min Act: -0.0001

Data Index: 550451 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 0.5149. Min Range: -0.5149

Max Act: 0.4047. Min Act: -0.0001

Data Index: 993364 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 0.5149. Min Range: -0.5149

Max Act: 0.4018. Min Act: -0.0001

Data Index: 1322401 (C4 (Web Text))

Max Activating Token Index: 462

Text #13

Max Range: 0.5149. Min Range: -0.5149

Max Act: 0.3974. Min Act: -0.0001

Data Index: 411445 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 0.5149. Min Range: -0.5149

Max Act: 0.4048. Min Act: -0.0001

Data Index: 16685 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 0.5149. Min Range: -0.5149

Max Act: 0.3900. Min Act: -0.0001

Data Index: 81495 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 0.5149. Min Range: -0.5149

Max Act: 0.3954. Min Act: -0.0000

Data Index: 697727 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 0.5149. Min Range: -0.5149

Max Act: 0.3946. Min Act: -0.0000

Data Index: 1258631 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 0.5149. Min Range: -0.5149

Max Act: 0.4016. Min Act: -0.0001

Data Index: 565879 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 0.5149. Min Range: -0.5149

Max Act: 0.3881. Min Act: -0.0001

Data Index: 139767 (C4 (Web Text))

Max Activating Token Index: 489