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

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

Neuron 2584 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: 1.6934. Min Range: -1.6934

Max Act: 1.6934. Min Act: -0.0000

Data Index: 776577 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 1.6934. Min Range: -1.6934

Max Act: 1.6148. Min Act: -0.0000

Data Index: 867959 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 1.6934. Min Range: -1.6934

Max Act: 1.6780. Min Act: -0.0000

Data Index: 355921 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 1.6934. Min Range: -1.6934

Max Act: 1.5707. Min Act: -0.0000

Data Index: 869049 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 1.6934. Min Range: -1.6934

Max Act: 1.6348. Min Act: -0.0000

Data Index: 546295 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 1.6934. Min Range: -1.6934

Max Act: 1.5296. Min Act: -0.0000

Data Index: 746000 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 1.6934. Min Range: -1.6934

Max Act: 1.6082. Min Act: -0.0000

Data Index: 598554 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 1.6934. Min Range: -1.6934

Max Act: 1.5793. Min Act: -0.0000

Data Index: 678479 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 1.6934. Min Range: -1.6934

Max Act: 1.5739. Min Act: -0.0000

Data Index: 339177 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 1.6934. Min Range: -1.6934

Max Act: 1.5695. Min Act: -0.0000

Data Index: 542422 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 1.6934. Min Range: -1.6934

Max Act: 1.6305. Min Act: -0.0000

Data Index: 77353 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 1.6934. Min Range: -1.6934

Max Act: 1.5145. Min Act: -0.0000

Data Index: 860211 (C4 (Web Text))

Max Activating Token Index: 126

Text #12

Max Range: 1.6934. Min Range: -1.6934

Max Act: 1.5041. Min Act: -0.0000

Data Index: 814621 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 1.6934. Min Range: -1.6934

Max Act: 1.5867. Min Act: -0.0000

Data Index: 1303257 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 1.6934. Min Range: -1.6934

Max Act: 1.4873. Min Act: -0.0000

Data Index: 213724 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 1.6934. Min Range: -1.6934

Max Act: 1.5678. Min Act: -0.0000

Data Index: 121522 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 1.6934. Min Range: -1.6934

Max Act: 1.4886. Min Act: -0.0000

Data Index: 332887 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 1.6934. Min Range: -1.6934

Max Act: 1.4530. Min Act: -0.0000

Data Index: 890002 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 1.6934. Min Range: -1.6934

Max Act: 1.5477. Min Act: -0.0000

Data Index: 636159 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 1.6934. Min Range: -1.6934

Max Act: 1.4371. Min Act: -0.0000

Data Index: 354607 (C4 (Web Text))

Max Activating Token Index: 663