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

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

Neuron 1755 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.1236. Min Act: -0.0001

Data Index: 1113734 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.1014. Min Act: -0.0001

Data Index: 1026512 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.1084. Min Act: -0.0001

Data Index: 963518 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.0999. Min Act: -0.0001

Data Index: 487814 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.0997. Min Act: -0.0001

Data Index: 1036841 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.0896. Min Act: -0.0001

Data Index: 238289 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.0900. Min Act: -0.0001

Data Index: 648232 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.0990. Min Act: -0.0001

Data Index: 784082 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.0902. Min Act: -0.0001

Data Index: 215301 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.0860. Min Act: -0.0001

Data Index: 616581 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.0898. Min Act: -0.0001

Data Index: 1317240 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.0912. Min Act: -0.0001

Data Index: 432674 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.0915. Min Act: -0.0001

Data Index: 127462 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.0903. Min Act: -0.0001

Data Index: 340985 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.0812. Min Act: -0.0001

Data Index: 649628 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.0911. Min Act: -0.0001

Data Index: 596005 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.0823. Min Act: -0.0001

Data Index: 542416 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.0833. Min Act: -0.0001

Data Index: 1020603 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.0815. Min Act: -0.0001

Data Index: 727532 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.0875. Min Act: -0.0001

Data Index: 543760 (C4 (Web Text))

Max Activating Token Index: 631