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

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

Neuron 2256 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.8800. Min Act: -0.0000

Data Index: 963870 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.8957. Min Act: -0.0000

Data Index: 956252 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 1.0258. Min Range: -1.0258

Max Act: 1.0258. Min Act: -0.0000

Data Index: 628625 (C4 (Web Text))

Max Activating Token Index: 237

Text #3

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.9069. Min Act: -0.0000

Data Index: 346033 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.8774. Min Act: -0.0000

Data Index: 322608 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.7489. Min Act: -0.0000

Data Index: 742835 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.7699. Min Act: -0.0000

Data Index: 180416 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.7945. Min Act: -0.0000

Data Index: 662918 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.7492. Min Act: -0.0000

Data Index: 265834 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.7684. Min Act: -0.0000

Data Index: 1102430 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.6871. Min Act: -0.0000

Data Index: 1593632 (Python Code)

Max Activating Token Index: 787

Text #11

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.7140. Min Act: -0.0000

Data Index: 473057 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.7222. Min Act: -0.0000

Data Index: 1348204 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.7060. Min Act: -0.0000

Data Index: 535919 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.7124. Min Act: -0.0000

Data Index: 99307 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.6380. Min Act: -0.0000

Data Index: 899485 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.6463. Min Act: -0.0000

Data Index: 597991 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.6493. Min Act: -0.0000

Data Index: 1169557 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.6190. Min Act: -0.0000

Data Index: 1238677 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.5818. Min Act: -0.0000

Data Index: 461404 (C4 (Web Text))

Max Activating Token Index: 979