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

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

Neuron 894 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: 0.9473. Min Range: -0.9473

Max Act: 0.8952. Min Act: -0.0000

Data Index: 516988 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.8316. Min Act: -0.0000

Data Index: 701425 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.9473. Min Act: -0.0000

Data Index: 297280 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.8750. Min Act: -0.0000

Data Index: 567680 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.8831. Min Act: -0.0000

Data Index: 1063963 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.8606. Min Act: -0.0000

Data Index: 56243 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.8936. Min Act: -0.0000

Data Index: 828105 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.8452. Min Act: -0.0000

Data Index: 1354201 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.8508. Min Act: -0.0000

Data Index: 116889 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.8333. Min Act: -0.0000

Data Index: 442558 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.8638. Min Act: -0.0000

Data Index: 109086 (C4 (Web Text))

Max Activating Token Index: 659

Text #11

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.8059. Min Act: -0.0000

Data Index: 1350557 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.8271. Min Act: -0.0000

Data Index: 902349 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.7980. Min Act: -0.0000

Data Index: 240825 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.8143. Min Act: -0.0000

Data Index: 132287 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.8258. Min Act: -0.0000

Data Index: 431096 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.7710. Min Act: -0.0000

Data Index: 1045878 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.8013. Min Act: -0.0000

Data Index: 874045 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.7787. Min Act: -0.0000

Data Index: 566495 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.7160. Min Act: 0.0000

Data Index: 614034 (C4 (Web Text))

Max Activating Token Index: 653