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

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

Neuron 5552 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.4752. Min Act: -0.0000

Data Index: 309485 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.4896. Min Act: -0.0001

Data Index: 671154 (C4 (Web Text))

Max Activating Token Index: 809

Text #2

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.4575. Min Act: -0.0000

Data Index: 400625 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.4256. Min Act: -0.0000

Data Index: 363866 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.4268. Min Act: -0.0001

Data Index: 795231 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3723. Min Act: -0.0001

Data Index: 626924 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3991. Min Act: -0.0001

Data Index: 721409 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.4036. Min Act: -0.0001

Data Index: 748228 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3632. Min Act: -0.0001

Data Index: 938753 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3748. Min Act: -0.0001

Data Index: 42082 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3945. Min Act: -0.0001

Data Index: 339209 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3915. Min Act: -0.0000

Data Index: 784076 (C4 (Web Text))

Max Activating Token Index: 972

Text #12

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3974. Min Act: -0.0000

Data Index: 324964 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3825. Min Act: -0.0000

Data Index: 596876 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3694. Min Act: -0.0001

Data Index: 396756 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3791. Min Act: -0.0000

Data Index: 1143365 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3473. Min Act: -0.0000

Data Index: 1048495 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3723. Min Act: -0.0001

Data Index: 488616 (C4 (Web Text))

Max Activating Token Index: 468

Text #18

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3841. Min Act: -0.0001

Data Index: 474 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3835. Min Act: -0.0000

Data Index: 615332 (C4 (Web Text))

Max Activating Token Index: 579