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

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

Neuron 5658 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0306. Min Range: -1.0306

Max Act: 1.0306. Min Act: -0.0000

Data Index: 63578 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.9655. Min Act: -0.0000

Data Index: 1332664 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8691. Min Act: -0.0000

Data Index: 586847 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.9053. Min Act: -0.0000

Data Index: 451985 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8957. Min Act: -0.0000

Data Index: 937987 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8661. Min Act: -0.0000

Data Index: 10446 (C4 (Web Text))

Max Activating Token Index: 415

Text #6

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8616. Min Act: -0.0000

Data Index: 180668 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8655. Min Act: -0.0000

Data Index: 576545 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8416. Min Act: -0.0000

Data Index: 899120 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8134. Min Act: -0.0000

Data Index: 451743 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7948. Min Act: -0.0000

Data Index: 228129 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7372. Min Act: -0.0000

Data Index: 1120343 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7848. Min Act: -0.0000

Data Index: 1080986 (C4 (Web Text))

Max Activating Token Index: 402

Text #13

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7507. Min Act: -0.0000

Data Index: 82961 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7481. Min Act: -0.0000

Data Index: 253076 (C4 (Web Text))

Max Activating Token Index: 444

Text #15

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7414. Min Act: -0.0000

Data Index: 391785 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7379. Min Act: -0.0000

Data Index: 31406 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7322. Min Act: -0.0000

Data Index: 241203 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7336. Min Act: -0.0000

Data Index: 832820 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7339. Min Act: -0.0000

Data Index: 64515 (C4 (Web Text))

Max Activating Token Index: 39