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

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

Neuron 2240 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2084. Min Range: -4.2084

Max Act: 4.2084. Min Act: -0.0001

Data Index: 760707 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 4.2084. Min Range: -4.2084

Max Act: 3.7825. Min Act: -0.0001

Data Index: 976570 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 4.2084. Min Range: -4.2084

Max Act: 3.5042. Min Act: -0.0001

Data Index: 1325745 (C4 (Web Text))

Max Activating Token Index: 169

Text #3

Max Range: 4.2084. Min Range: -4.2084

Max Act: 3.4500. Min Act: -0.0001

Data Index: 1003598 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 4.2084. Min Range: -4.2084

Max Act: 3.1889. Min Act: -0.0001

Data Index: 1247188 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 4.2084. Min Range: -4.2084

Max Act: 3.1548. Min Act: -0.0000

Data Index: 848222 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 4.2084. Min Range: -4.2084

Max Act: 3.1034. Min Act: -0.0001

Data Index: 784185 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 4.2084. Min Range: -4.2084

Max Act: 3.2717. Min Act: -0.0001

Data Index: 800872 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 4.2084. Min Range: -4.2084

Max Act: 3.1540. Min Act: -0.0000

Data Index: 214204 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 4.2084. Min Range: -4.2084

Max Act: 2.8513. Min Act: -0.0001

Data Index: 30816 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 4.2084. Min Range: -4.2084

Max Act: 2.7861. Min Act: -0.0001

Data Index: 479678 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 4.2084. Min Range: -4.2084

Max Act: 2.7849. Min Act: -0.0001

Data Index: 523767 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 4.2084. Min Range: -4.2084

Max Act: 2.8217. Min Act: -0.0001

Data Index: 925832 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 4.2084. Min Range: -4.2084

Max Act: 2.9452. Min Act: -0.0001

Data Index: 1343251 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 4.2084. Min Range: -4.2084

Max Act: 2.7778. Min Act: -0.0000

Data Index: 1147922 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 4.2084. Min Range: -4.2084

Max Act: 2.7819. Min Act: -0.0000

Data Index: 607873 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 4.2084. Min Range: -4.2084

Max Act: 2.7817. Min Act: -0.0001

Data Index: 706837 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 4.2084. Min Range: -4.2084

Max Act: 2.7646. Min Act: -0.0000

Data Index: 886370 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 4.2084. Min Range: -4.2084

Max Act: 2.9152. Min Act: -0.0000

Data Index: 586967 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 4.2084. Min Range: -4.2084

Max Act: 2.6205. Min Act: -0.0001

Data Index: 1119410 (C4 (Web Text))

Max Activating Token Index: 162