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

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

Neuron 1970 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: 1.5662. Min Range: -1.5662

Max Act: 1.5662. Min Act: -0.0000

Data Index: 240814 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.1140. Min Act: -0.0000

Data Index: 288961 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.0244. Min Act: -0.0000

Data Index: 661377 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 1.5662. Min Range: -1.5662

Max Act: 0.8752. Min Act: -0.0000

Data Index: 1137839 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 1.5662. Min Range: -1.5662

Max Act: 0.8657. Min Act: -0.0000

Data Index: 1309602 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 1.5662. Min Range: -1.5662

Max Act: 0.8884. Min Act: -0.0000

Data Index: 796201 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 1.5662. Min Range: -1.5662

Max Act: 0.8727. Min Act: -0.0000

Data Index: 492026 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 1.5662. Min Range: -1.5662

Max Act: 0.8797. Min Act: -0.0000

Data Index: 1103983 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 1.5662. Min Range: -1.5662

Max Act: 0.8074. Min Act: -0.0000

Data Index: 321040 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 1.5662. Min Range: -1.5662

Max Act: 0.8611. Min Act: -0.0000

Data Index: 1030336 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 1.5662. Min Range: -1.5662

Max Act: 0.8617. Min Act: -0.0000

Data Index: 859300 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 1.5662. Min Range: -1.5662

Max Act: 0.8291. Min Act: -0.0000

Data Index: 472934 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 1.5662. Min Range: -1.5662

Max Act: 0.8178. Min Act: -0.0000

Data Index: 1120184 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 1.5662. Min Range: -1.5662

Max Act: 0.7443. Min Act: -0.0000

Data Index: 1140628 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 1.5662. Min Range: -1.5662

Max Act: 0.7204. Min Act: -0.0000

Data Index: 506490 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 1.5662. Min Range: -1.5662

Max Act: 0.7885. Min Act: -0.0000

Data Index: 83104 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 1.5662. Min Range: -1.5662

Max Act: 0.7907. Min Act: -0.0000

Data Index: 52099 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 1.5662. Min Range: -1.5662

Max Act: 0.7583. Min Act: -0.0000

Data Index: 597315 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 1.5662. Min Range: -1.5662

Max Act: 0.7396. Min Act: -0.0000

Data Index: 760129 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 1.5662. Min Range: -1.5662

Max Act: 0.7984. Min Act: -0.0000

Data Index: 1170043 (C4 (Web Text))

Max Activating Token Index: 675