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

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

Neuron 4380 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8765. Min Range: -0.8765

Max Act: 0.8765. Min Act: -0.0000

Data Index: 610632 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 0.8765. Min Range: -0.8765

Max Act: 0.6470. Min Act: -0.0000

Data Index: 786378 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 0.8765. Min Range: -0.8765

Max Act: 0.6506. Min Act: -0.0000

Data Index: 375468 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 0.8765. Min Range: -0.8765

Max Act: 0.7488. Min Act: -0.0000

Data Index: 1066230 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 0.8765. Min Range: -0.8765

Max Act: 0.6880. Min Act: -0.0000

Data Index: 1146416 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 0.8765. Min Range: -0.8765

Max Act: 0.6544. Min Act: -0.0000

Data Index: 1079386 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 0.8765. Min Range: -0.8765

Max Act: 0.6583. Min Act: -0.0000

Data Index: 171276 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 0.8765. Min Range: -0.8765

Max Act: 0.5819. Min Act: -0.0000

Data Index: 735858 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 0.8765. Min Range: -0.8765

Max Act: 0.6158. Min Act: -0.0000

Data Index: 931794 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 0.8765. Min Range: -0.8765

Max Act: 0.5992. Min Act: -0.0000

Data Index: 507656 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 0.8765. Min Range: -0.8765

Max Act: 0.5676. Min Act: -0.0000

Data Index: 843547 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 0.8765. Min Range: -0.8765

Max Act: 0.6763. Min Act: -0.0000

Data Index: 176489 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 0.8765. Min Range: -0.8765

Max Act: 0.6214. Min Act: -0.0000

Data Index: 692028 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 0.8765. Min Range: -0.8765

Max Act: 0.6137. Min Act: -0.0000

Data Index: 1059367 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 0.8765. Min Range: -0.8765

Max Act: 0.6024. Min Act: -0.0000

Data Index: 343444 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 0.8765. Min Range: -0.8765

Max Act: 0.5438. Min Act: -0.0000

Data Index: 1105672 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 0.8765. Min Range: -0.8765

Max Act: 0.5754. Min Act: -0.0000

Data Index: 733071 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 0.8765. Min Range: -0.8765

Max Act: 0.5597. Min Act: -0.0000

Data Index: 1439899 (Python Code)

Max Activating Token Index: 565

Text #18

Max Range: 0.8765. Min Range: -0.8765

Max Act: 0.5927. Min Act: -0.0000

Data Index: 860610 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 0.8765. Min Range: -0.8765

Max Act: 0.6063. Min Act: -0.0000

Data Index: 114362 (C4 (Web Text))

Max Activating Token Index: 592