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

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

Neuron 3758 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: 0.6632. Min Range: -0.6632

Max Act: 0.6413. Min Act: -0.0000

Data Index: 217890 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.6632. Min Range: -0.6632

Max Act: 0.6632. Min Act: -0.0000

Data Index: 705078 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 0.6632. Min Range: -0.6632

Max Act: 0.6244. Min Act: -0.0000

Data Index: 569052 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 0.6632. Min Range: -0.6632

Max Act: 0.6255. Min Act: -0.0000

Data Index: 570778 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 0.6632. Min Range: -0.6632

Max Act: 0.5862. Min Act: -0.0000

Data Index: 149408 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 0.6632. Min Range: -0.6632

Max Act: 0.5913. Min Act: -0.0000

Data Index: 1216413 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 0.6632. Min Range: -0.6632

Max Act: 0.5699. Min Act: -0.0000

Data Index: 1219581 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 0.6632. Min Range: -0.6632

Max Act: 0.5534. Min Act: -0.0000

Data Index: 476607 (C4 (Web Text))

Max Activating Token Index: 588

Text #8

Max Range: 0.6632. Min Range: -0.6632

Max Act: 0.5739. Min Act: -0.0000

Data Index: 197168 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 0.6632. Min Range: -0.6632

Max Act: 0.5658. Min Act: -0.0000

Data Index: 63386 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 0.6632. Min Range: -0.6632

Max Act: 0.5049. Min Act: -0.0000

Data Index: 1013581 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 0.6632. Min Range: -0.6632

Max Act: 0.5440. Min Act: -0.0000

Data Index: 983472 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 0.6632. Min Range: -0.6632

Max Act: 0.5235. Min Act: 0.0000

Data Index: 23656 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 0.6632. Min Range: -0.6632

Max Act: 0.5357. Min Act: -0.0000

Data Index: 166600 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 0.6632. Min Range: -0.6632

Max Act: 0.5504. Min Act: -0.0000

Data Index: 1070525 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 0.6632. Min Range: -0.6632

Max Act: 0.5172. Min Act: -0.0000

Data Index: 533699 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 0.6632. Min Range: -0.6632

Max Act: 0.5346. Min Act: -0.0000

Data Index: 1153090 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 0.6632. Min Range: -0.6632

Max Act: 0.5077. Min Act: -0.0000

Data Index: 1473217 (Python Code)

Max Activating Token Index: 935

Text #18

Max Range: 0.6632. Min Range: -0.6632

Max Act: 0.5203. Min Act: -0.0000

Data Index: 754219 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 0.6632. Min Range: -0.6632

Max Act: 0.4906. Min Act: -0.0000

Data Index: 1457254 (Python Code)

Max Activating Token Index: 5