Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3452 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7457. Min Range: -0.7457

Max Act: 0.7457. Min Act: -0.0003

Data Index: 266 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 0.7457. Min Range: -0.7457

Max Act: 0.6717. Min Act: -0.0003

Data Index: 87786 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 0.7457. Min Range: -0.7457

Max Act: 0.7010. Min Act: -0.0003

Data Index: 370986 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 0.7457. Min Range: -0.7457

Max Act: 0.6762. Min Act: -0.0003

Data Index: 1085135 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 0.7457. Min Range: -0.7457

Max Act: 0.6001. Min Act: -0.0003

Data Index: 124404 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 0.7457. Min Range: -0.7457

Max Act: 0.6510. Min Act: -0.0003

Data Index: 1224964 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 0.7457. Min Range: -0.7457

Max Act: 0.5731. Min Act: -0.0003

Data Index: 284244 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 0.7457. Min Range: -0.7457

Max Act: 0.6439. Min Act: -0.0003

Data Index: 82212 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 0.7457. Min Range: -0.7457

Max Act: 0.6446. Min Act: -0.0003

Data Index: 765094 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 0.7457. Min Range: -0.7457

Max Act: 0.6024. Min Act: -0.0003

Data Index: 642870 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 0.7457. Min Range: -0.7457

Max Act: 0.6625. Min Act: -0.0003

Data Index: 859692 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 0.7457. Min Range: -0.7457

Max Act: 0.6557. Min Act: -0.0003

Data Index: 202116 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 0.7457. Min Range: -0.7457

Max Act: 0.6379. Min Act: -0.0003

Data Index: 1318085 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 0.7457. Min Range: -0.7457

Max Act: 0.5765. Min Act: -0.0003

Data Index: 3090 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 0.7457. Min Range: -0.7457

Max Act: 0.6511. Min Act: -0.0003

Data Index: 1900 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 0.7457. Min Range: -0.7457

Max Act: 0.6512. Min Act: -0.0003

Data Index: 886621 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 0.7457. Min Range: -0.7457

Max Act: 0.6262. Min Act: -0.0003

Data Index: 234045 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 0.7457. Min Range: -0.7457

Max Act: 0.6509. Min Act: -0.0003

Data Index: 252079 (C4 (Web Text))

Max Activating Token Index: 513

Text #18

Max Range: 0.7457. Min Range: -0.7457

Max Act: 0.6442. Min Act: -0.0003

Data Index: 1152317 (C4 (Web Text))

Max Activating Token Index: 268

Text #19

Max Range: 0.7457. Min Range: -0.7457

Max Act: 0.6433. Min Act: -0.0003

Data Index: 786960 (C4 (Web Text))

Max Activating Token Index: 995