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

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

Neuron 5323 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: 2.4284. Min Range: -2.4284

Max Act: 2.4284. Min Act: -0.0000

Data Index: 827599 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 2.4284. Min Range: -2.4284

Max Act: 2.2944. Min Act: -0.0000

Data Index: 403932 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 2.4284. Min Range: -2.4284

Max Act: 2.2841. Min Act: -0.0000

Data Index: 675073 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 2.4284. Min Range: -2.4284

Max Act: 1.9337. Min Act: -0.0000

Data Index: 93016 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 2.4284. Min Range: -2.4284

Max Act: 1.8936. Min Act: -0.0000

Data Index: 506750 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 2.4284. Min Range: -2.4284

Max Act: 1.9449. Min Act: -0.0000

Data Index: 441393 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 2.4284. Min Range: -2.4284

Max Act: 1.8772. Min Act: -0.0000

Data Index: 1157464 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 2.4284. Min Range: -2.4284

Max Act: 1.8461. Min Act: -0.0000

Data Index: 260679 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 2.4284. Min Range: -2.4284

Max Act: 1.9402. Min Act: -0.0000

Data Index: 334277 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 2.4284. Min Range: -2.4284

Max Act: 1.8823. Min Act: -0.0000

Data Index: 472933 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 2.4284. Min Range: -2.4284

Max Act: 1.7798. Min Act: -0.0000

Data Index: 601528 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 2.4284. Min Range: -2.4284

Max Act: 1.8683. Min Act: -0.0000

Data Index: 835677 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 2.4284. Min Range: -2.4284

Max Act: 1.7447. Min Act: -0.0000

Data Index: 163807 (C4 (Web Text))

Max Activating Token Index: 687

Text #13

Max Range: 2.4284. Min Range: -2.4284

Max Act: 1.6103. Min Act: -0.0000

Data Index: 59565 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 2.4284. Min Range: -2.4284

Max Act: 1.8967. Min Act: -0.0000

Data Index: 1164003 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 2.4284. Min Range: -2.4284

Max Act: 1.6670. Min Act: -0.0000

Data Index: 876550 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 2.4284. Min Range: -2.4284

Max Act: 1.6586. Min Act: -0.0000

Data Index: 517099 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 2.4284. Min Range: -2.4284

Max Act: 1.5536. Min Act: -0.0000

Data Index: 28149 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 2.4284. Min Range: -2.4284

Max Act: 1.5472. Min Act: -0.0000

Data Index: 536320 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 2.4284. Min Range: -2.4284

Max Act: 1.6210. Min Act: -0.0000

Data Index: 471823 (C4 (Web Text))

Max Activating Token Index: 439