Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2836 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7026. Min Range: -1.7026

Max Act: 1.7026. Min Act: -0.0001

Data Index: 192010 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 1.7026. Min Range: -1.7026

Max Act: 1.6313. Min Act: -0.0001

Data Index: 1232331 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 1.7026. Min Range: -1.7026

Max Act: 1.6922. Min Act: -0.0001

Data Index: 876196 (C4 (Web Text))

Max Activating Token Index: 361

Text #3

Max Range: 1.7026. Min Range: -1.7026

Max Act: 1.6983. Min Act: -0.0001

Data Index: 756874 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 1.7026. Min Range: -1.7026

Max Act: 1.6448. Min Act: -0.0001

Data Index: 936562 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 1.7026. Min Range: -1.7026

Max Act: 1.5223. Min Act: -0.0001

Data Index: 417177 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 1.7026. Min Range: -1.7026

Max Act: 1.4821. Min Act: -0.0001

Data Index: 245713 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 1.7026. Min Range: -1.7026

Max Act: 1.4301. Min Act: -0.0001

Data Index: 256963 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 1.7026. Min Range: -1.7026

Max Act: 1.4863. Min Act: -0.0001

Data Index: 768614 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 1.7026. Min Range: -1.7026

Max Act: 1.2544. Min Act: -0.0001

Data Index: 997235 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 1.7026. Min Range: -1.7026

Max Act: 1.4266. Min Act: -0.0001

Data Index: 1198375 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 1.7026. Min Range: -1.7026

Max Act: 1.4608. Min Act: -0.0001

Data Index: 1090273 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 1.7026. Min Range: -1.7026

Max Act: 1.3333. Min Act: -0.0001

Data Index: 8871 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 1.7026. Min Range: -1.7026

Max Act: 1.4106. Min Act: -0.0001

Data Index: 828128 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 1.7026. Min Range: -1.7026

Max Act: 1.3877. Min Act: -0.0001

Data Index: 967365 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 1.7026. Min Range: -1.7026

Max Act: 1.1971. Min Act: -0.0001

Data Index: 255611 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 1.7026. Min Range: -1.7026

Max Act: 1.2695. Min Act: -0.0001

Data Index: 962353 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 1.7026. Min Range: -1.7026

Max Act: 1.5492. Min Act: -0.0001

Data Index: 1257737 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 1.7026. Min Range: -1.7026

Max Act: 1.3945. Min Act: -0.0001

Data Index: 850447 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 1.7026. Min Range: -1.7026

Max Act: 1.3391. Min Act: -0.0001

Data Index: 276356 (C4 (Web Text))

Max Activating Token Index: 734