Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1319 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.7597. Min Act: -0.0002

Data Index: 413586 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.7368. Min Act: -0.0002

Data Index: 1342951 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.7034. Min Act: -0.0002

Data Index: 713414 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.6729. Min Act: -0.0002

Data Index: 307908 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.6762. Min Act: -0.0003

Data Index: 275281 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.6708. Min Act: -0.0003

Data Index: 763055 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.6649. Min Act: -0.0003

Data Index: 270962 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.6961. Min Act: -0.0003

Data Index: 366894 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.6526. Min Act: -0.0002

Data Index: 669996 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.6507. Min Act: -0.0003

Data Index: 553686 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.6490. Min Act: -0.0003

Data Index: 604383 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.6461. Min Act: -0.0003

Data Index: 1340224 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.6243. Min Act: -0.0003

Data Index: 1089778 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.6643. Min Act: -0.0002

Data Index: 551662 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.6295. Min Act: -0.0003

Data Index: 171338 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.6262. Min Act: -0.0003

Data Index: 667659 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.6081. Min Act: -0.0003

Data Index: 237012 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.6045. Min Act: -0.0003

Data Index: 994150 (C4 (Web Text))

Max Activating Token Index: 325

Text #18

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.6204. Min Act: -0.0003

Data Index: 658901 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.5813. Min Act: -0.0003

Data Index: 691735 (C4 (Web Text))

Max Activating Token Index: 854