Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1924 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.7639. Min Act: -0.0001

Data Index: 158410 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.7940. Min Act: -0.0001

Data Index: 463747 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.7463. Min Act: -0.0001

Data Index: 1323612 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.8284. Min Act: -0.0001

Data Index: 295851 (C4 (Web Text))

Max Activating Token Index: 292

Text #4

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.7438. Min Act: -0.0001

Data Index: 581484 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.6286. Min Act: -0.0001

Data Index: 327472 (C4 (Web Text))

Max Activating Token Index: 586

Text #6

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.8097. Min Act: -0.0001

Data Index: 219701 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.6981. Min Act: -0.0001

Data Index: 955342 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.7480. Min Act: -0.0001

Data Index: 364863 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.7463. Min Act: -0.0001

Data Index: 129042 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.7026. Min Act: -0.0001

Data Index: 448081 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.7136. Min Act: -0.0001

Data Index: 662936 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.6883. Min Act: -0.0001

Data Index: 1105864 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.7020. Min Act: -0.0001

Data Index: 894879 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.7006. Min Act: -0.0001

Data Index: 229498 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.7408. Min Act: -0.0001

Data Index: 1148214 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.6545. Min Act: -0.0001

Data Index: 222371 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.7309. Min Act: -0.0001

Data Index: 869087 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.6795. Min Act: -0.0001

Data Index: 182440 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.6295. Min Act: -0.0001

Data Index: 1094719 (C4 (Web Text))

Max Activating Token Index: 920