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

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

Neuron 1651 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3967. Min Range: -0.3967

Max Act: 0.3967. Min Act: -0.0000

Data Index: 440931 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 0.3967. Min Range: -0.3967

Max Act: 0.3864. Min Act: -0.0000

Data Index: 1111074 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 0.3967. Min Range: -0.3967

Max Act: 0.3620. Min Act: -0.0000

Data Index: 554325 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 0.3967. Min Range: -0.3967

Max Act: 0.3682. Min Act: -0.0000

Data Index: 136123 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 0.3967. Min Range: -0.3967

Max Act: 0.3779. Min Act: -0.0000

Data Index: 29044 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 0.3967. Min Range: -0.3967

Max Act: 0.3242. Min Act: -0.0000

Data Index: 303392 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 0.3967. Min Range: -0.3967

Max Act: 0.3579. Min Act: -0.0000

Data Index: 5165 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 0.3967. Min Range: -0.3967

Max Act: 0.3639. Min Act: -0.0000

Data Index: 4574 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 0.3967. Min Range: -0.3967

Max Act: 0.3389. Min Act: -0.0000

Data Index: 689022 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 0.3967. Min Range: -0.3967

Max Act: 0.3488. Min Act: -0.0000

Data Index: 857020 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 0.3967. Min Range: -0.3967

Max Act: 0.3487. Min Act: -0.0000

Data Index: 873857 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 0.3967. Min Range: -0.3967

Max Act: 0.3349. Min Act: -0.0000

Data Index: 468938 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 0.3967. Min Range: -0.3967

Max Act: 0.3129. Min Act: -0.0000

Data Index: 469067 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 0.3967. Min Range: -0.3967

Max Act: 0.3400. Min Act: -0.0000

Data Index: 1092025 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 0.3967. Min Range: -0.3967

Max Act: 0.3340. Min Act: -0.0000

Data Index: 282977 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 0.3967. Min Range: -0.3967

Max Act: 0.3303. Min Act: -0.0000

Data Index: 14372 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 0.3967. Min Range: -0.3967

Max Act: 0.3288. Min Act: -0.0000

Data Index: 1139882 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.3967. Min Range: -0.3967

Max Act: 0.3195. Min Act: -0.0000

Data Index: 452373 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 0.3967. Min Range: -0.3967

Max Act: 0.3519. Min Act: -0.0000

Data Index: 1249555 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 0.3967. Min Range: -0.3967

Max Act: 0.3287. Min Act: -0.0000

Data Index: 448880 (C4 (Web Text))

Max Activating Token Index: 447