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

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

Neuron 3030 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7076. Min Range: -5.7076

Max Act: 5.7076. Min Act: -0.0000

Data Index: 1130824 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 5.7076. Min Range: -5.7076

Max Act: 5.6688. Min Act: -0.0000

Data Index: 1127028 (C4 (Web Text))

Max Activating Token Index: 530

Text #2

Max Range: 5.7076. Min Range: -5.7076

Max Act: 4.8829. Min Act: -0.0000

Data Index: 89339 (C4 (Web Text))

Max Activating Token Index: 846

Text #3

Max Range: 5.7076. Min Range: -5.7076

Max Act: 4.7276. Min Act: -0.0000

Data Index: 473766 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 5.7076. Min Range: -5.7076

Max Act: 4.8577. Min Act: -0.0000

Data Index: 1111865 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 5.7076. Min Range: -5.7076

Max Act: 5.1846. Min Act: -0.0000

Data Index: 982395 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 5.7076. Min Range: -5.7076

Max Act: 4.7353. Min Act: -0.0000

Data Index: 1157174 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 5.7076. Min Range: -5.7076

Max Act: 4.8291. Min Act: -0.0000

Data Index: 453131 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 5.7076. Min Range: -5.7076

Max Act: 4.5049. Min Act: -0.0000

Data Index: 892057 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 5.7076. Min Range: -5.7076

Max Act: 4.4936. Min Act: -0.0000

Data Index: 223822 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 5.7076. Min Range: -5.7076

Max Act: 4.4240. Min Act: -0.0000

Data Index: 1104080 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 5.7076. Min Range: -5.7076

Max Act: 4.2008. Min Act: -0.0000

Data Index: 1145163 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 5.7076. Min Range: -5.7076

Max Act: 4.1413. Min Act: -0.0000

Data Index: 1022140 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 5.7076. Min Range: -5.7076

Max Act: 3.8664. Min Act: -0.0000

Data Index: 602534 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 5.7076. Min Range: -5.7076

Max Act: 3.8996. Min Act: -0.0000

Data Index: 511736 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 5.7076. Min Range: -5.7076

Max Act: 3.9704. Min Act: -0.0000

Data Index: 714665 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 5.7076. Min Range: -5.7076

Max Act: 3.9413. Min Act: -0.0000

Data Index: 1319641 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 5.7076. Min Range: -5.7076

Max Act: 4.0403. Min Act: -0.0000

Data Index: 1095647 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 5.7076. Min Range: -5.7076

Max Act: 3.6966. Min Act: -0.0000

Data Index: 105186 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 5.7076. Min Range: -5.7076

Max Act: 3.6638. Min Act: -0.0000

Data Index: 273217 (C4 (Web Text))

Max Activating Token Index: 163