Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 733 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.8260. Min Act: -0.0001

Data Index: 218733 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.7712. Min Act: -0.0001

Data Index: 785054 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.7128. Min Act: -0.0001

Data Index: 1242302 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.6951. Min Act: -0.0001

Data Index: 1239619 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.7624. Min Act: -0.0001

Data Index: 213496 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.7336. Min Act: -0.0001

Data Index: 957034 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.7003. Min Act: -0.0001

Data Index: 195404 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.7409. Min Act: -0.0001

Data Index: 1280573 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.6903. Min Act: -0.0001

Data Index: 1325672 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.7027. Min Act: -0.0001

Data Index: 468535 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.6400. Min Act: -0.0001

Data Index: 689997 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.6401. Min Act: -0.0001

Data Index: 3131 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.6590. Min Act: -0.0001

Data Index: 924974 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.6327. Min Act: -0.0001

Data Index: 745473 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.5957. Min Act: -0.0001

Data Index: 501847 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.6674. Min Act: -0.0001

Data Index: 1082501 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.5955. Min Act: -0.0001

Data Index: 258970 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.6325. Min Act: -0.0001

Data Index: 1155625 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.6942. Min Act: -0.0001

Data Index: 280283 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.6039. Min Act: -0.0001

Data Index: 233966 (C4 (Web Text))

Max Activating Token Index: 994