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

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

Neuron 1174 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.5273. Min Act: -0.0000

Data Index: 221408 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.4966. Min Act: -0.0000

Data Index: 561308 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.4883. Min Act: -0.0000

Data Index: 611000 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.4798. Min Act: -0.0000

Data Index: 185341 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.4252. Min Act: -0.0000

Data Index: 965468 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.4323. Min Act: -0.0000

Data Index: 1165755 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.4095. Min Act: -0.0000

Data Index: 678661 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.4122. Min Act: -0.0000

Data Index: 1120877 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.3728. Min Act: -0.0000

Data Index: 321945 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.4051. Min Act: -0.0000

Data Index: 1009412 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.3894. Min Act: -0.0000

Data Index: 1268150 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.4020. Min Act: -0.0000

Data Index: 923250 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.3950. Min Act: -0.0000

Data Index: 1126117 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.3597. Min Act: -0.0000

Data Index: 947506 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.3830. Min Act: -0.0000

Data Index: 359229 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.3802. Min Act: -0.0000

Data Index: 138671 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.3837. Min Act: -0.0000

Data Index: 1163090 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.3820. Min Act: -0.0000

Data Index: 9804 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.3768. Min Act: -0.0000

Data Index: 1634824 (Python Code)

Max Activating Token Index: 809

Text #19

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.3902. Min Act: -0.0000

Data Index: 1314081 (C4 (Web Text))

Max Activating Token Index: 829