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

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

Neuron 5103 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: 2.5494. Min Range: -2.5494

Max Act: 2.5494. Min Act: -0.0000

Data Index: 1184752 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 2.5494. Min Range: -2.5494

Max Act: 1.8583. Min Act: -0.0000

Data Index: 145643 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 2.5494. Min Range: -2.5494

Max Act: 1.8211. Min Act: -0.0000

Data Index: 425647 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 2.5494. Min Range: -2.5494

Max Act: 1.8077. Min Act: -0.0000

Data Index: 1554918 (Python Code)

Max Activating Token Index: 271

Text #4

Max Range: 2.5494. Min Range: -2.5494

Max Act: 1.6938. Min Act: -0.0000

Data Index: 1084665 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 2.5494. Min Range: -2.5494

Max Act: 1.6452. Min Act: -0.0000

Data Index: 204675 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 2.5494. Min Range: -2.5494

Max Act: 1.6294. Min Act: -0.0000

Data Index: 1214281 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 2.5494. Min Range: -2.5494

Max Act: 1.6385. Min Act: -0.0000

Data Index: 1450770 (Python Code)

Max Activating Token Index: 359

Text #8

Max Range: 2.5494. Min Range: -2.5494

Max Act: 1.7003. Min Act: -0.0000

Data Index: 1503518 (Python Code)

Max Activating Token Index: 394

Text #9

Max Range: 2.5494. Min Range: -2.5494

Max Act: 1.5952. Min Act: -0.0000

Data Index: 1397373 (Python Code)

Max Activating Token Index: 147

Text #10

Max Range: 2.5494. Min Range: -2.5494

Max Act: 1.6015. Min Act: -0.0000

Data Index: 1565659 (Python Code)

Max Activating Token Index: 305

Text #11

Max Range: 2.5494. Min Range: -2.5494

Max Act: 1.5676. Min Act: -0.0000

Data Index: 404791 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 2.5494. Min Range: -2.5494

Max Act: 1.5112. Min Act: -0.0000

Data Index: 1411534 (Python Code)

Max Activating Token Index: 444

Text #13

Max Range: 2.5494. Min Range: -2.5494

Max Act: 1.5043. Min Act: -0.0000

Data Index: 1521516 (Python Code)

Max Activating Token Index: 232

Text #14

Max Range: 2.5494. Min Range: -2.5494

Max Act: 1.5181. Min Act: -0.0000

Data Index: 20555 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 2.5494. Min Range: -2.5494

Max Act: 1.5782. Min Act: -0.0000

Data Index: 155747 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 2.5494. Min Range: -2.5494

Max Act: 1.3831. Min Act: -0.0000

Data Index: 1642234 (Python Code)

Max Activating Token Index: 448

Text #17

Max Range: 2.5494. Min Range: -2.5494

Max Act: 1.3626. Min Act: -0.0000

Data Index: 1001190 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 2.5494. Min Range: -2.5494

Max Act: 1.3078. Min Act: -0.0000

Data Index: 1383122 (Python Code)

Max Activating Token Index: 289

Text #19

Max Range: 2.5494. Min Range: -2.5494

Max Act: 1.3887. Min Act: -0.0000

Data Index: 1386027 (Python Code)

Max Activating Token Index: 482