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

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

Neuron 3409 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4180. Min Range: -3.4180

Max Act: 3.4180. Min Act: -0.0000

Data Index: 346141 (C4 (Web Text))

Max Activating Token Index: 597

Text #1

Max Range: 3.4180. Min Range: -3.4180

Max Act: 3.2342. Min Act: -0.0000

Data Index: 645098 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 3.4180. Min Range: -3.4180

Max Act: 3.0216. Min Act: -0.0000

Data Index: 1274927 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 3.4180. Min Range: -3.4180

Max Act: 3.0605. Min Act: -0.0000

Data Index: 373086 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 3.4180. Min Range: -3.4180

Max Act: 2.5191. Min Act: -0.0000

Data Index: 671496 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 3.4180. Min Range: -3.4180

Max Act: 2.4863. Min Act: -0.0000

Data Index: 1190944 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 3.4180. Min Range: -3.4180

Max Act: 2.4896. Min Act: -0.0000

Data Index: 1220614 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 3.4180. Min Range: -3.4180

Max Act: 2.0309. Min Act: -0.0000

Data Index: 305526 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 3.4180. Min Range: -3.4180

Max Act: 2.3614. Min Act: -0.0000

Data Index: 165567 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 3.4180. Min Range: -3.4180

Max Act: 2.2407. Min Act: -0.0000

Data Index: 297584 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 3.4180. Min Range: -3.4180

Max Act: 2.0860. Min Act: -0.0000

Data Index: 1091668 (C4 (Web Text))

Max Activating Token Index: 888

Text #11

Max Range: 3.4180. Min Range: -3.4180

Max Act: 2.4835. Min Act: -0.0000

Data Index: 732486 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 3.4180. Min Range: -3.4180

Max Act: 2.0964. Min Act: -0.0000

Data Index: 864086 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 3.4180. Min Range: -3.4180

Max Act: 2.2939. Min Act: -0.0000

Data Index: 625189 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 3.4180. Min Range: -3.4180

Max Act: 2.0968. Min Act: -0.0000

Data Index: 901623 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 3.4180. Min Range: -3.4180

Max Act: 2.2608. Min Act: -0.0000

Data Index: 1300948 (C4 (Web Text))

Max Activating Token Index: 157

Text #16

Max Range: 3.4180. Min Range: -3.4180

Max Act: 2.0093. Min Act: -0.0000

Data Index: 630433 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 3.4180. Min Range: -3.4180

Max Act: 2.1002. Min Act: -0.0000

Data Index: 369243 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 3.4180. Min Range: -3.4180

Max Act: 2.0175. Min Act: -0.0000

Data Index: 775979 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 3.4180. Min Range: -3.4180

Max Act: 1.9631. Min Act: -0.0000

Data Index: 595243 (C4 (Web Text))

Max Activating Token Index: 697