Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5042 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.8538. Min Act: -0.0000

Data Index: 419506 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.6339. Min Act: -0.0000

Data Index: 872229 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.6429. Min Act: -0.0000

Data Index: 70871 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.5712. Min Act: -0.0000

Data Index: 419153 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.6014. Min Act: -0.0000

Data Index: 641246 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.5770. Min Act: -0.0000

Data Index: 510396 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.4876. Min Act: -0.0000

Data Index: 150389 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.4612. Min Act: -0.0000

Data Index: 689610 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.5198. Min Act: -0.0000

Data Index: 624564 (C4 (Web Text))

Max Activating Token Index: 234

Text #9

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.4969. Min Act: -0.0000

Data Index: 1106597 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.5846. Min Act: -0.0000

Data Index: 672483 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.4599. Min Act: -0.0000

Data Index: 384590 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.4836. Min Act: -0.0000

Data Index: 143434 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.4739. Min Act: -0.0000

Data Index: 1232012 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.4968. Min Act: -0.0000

Data Index: 14359 (C4 (Web Text))

Max Activating Token Index: 1007

Text #15

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.4605. Min Act: -0.0000

Data Index: 324887 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.4504. Min Act: -0.0000

Data Index: 460497 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.4650. Min Act: -0.0000

Data Index: 506448 (C4 (Web Text))

Max Activating Token Index: 181

Text #18

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.4420. Min Act: -0.0000

Data Index: 27158 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.4682. Min Act: -0.0000

Data Index: 851865 (C4 (Web Text))

Max Activating Token Index: 114