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

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

Neuron 1449 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4669. Min Range: -1.4669

Max Act: 1.4669. Min Act: -0.0000

Data Index: 1528512 (Python Code)

Max Activating Token Index: 739

Text #1

Max Range: 1.4669. Min Range: -1.4669

Max Act: 0.9786. Min Act: -0.0000

Data Index: 1242624 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 1.4669. Min Range: -1.4669

Max Act: 0.9518. Min Act: -0.0000

Data Index: 84906 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 1.4669. Min Range: -1.4669

Max Act: 0.9103. Min Act: -0.0000

Data Index: 264595 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 1.4669. Min Range: -1.4669

Max Act: 0.9338. Min Act: -0.0000

Data Index: 848942 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 1.4669. Min Range: -1.4669

Max Act: 0.9007. Min Act: -0.0000

Data Index: 1019705 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 1.4669. Min Range: -1.4669

Max Act: 0.8736. Min Act: -0.0000

Data Index: 583045 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 1.4669. Min Range: -1.4669

Max Act: 0.8715. Min Act: -0.0000

Data Index: 1532347 (Python Code)

Max Activating Token Index: 140

Text #8

Max Range: 1.4669. Min Range: -1.4669

Max Act: 0.8703. Min Act: -0.0000

Data Index: 836178 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 1.4669. Min Range: -1.4669

Max Act: 0.8435. Min Act: -0.0000

Data Index: 1465451 (Python Code)

Max Activating Token Index: 564

Text #10

Max Range: 1.4669. Min Range: -1.4669

Max Act: 0.7876. Min Act: -0.0000

Data Index: 790983 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 1.4669. Min Range: -1.4669

Max Act: 0.8349. Min Act: -0.0000

Data Index: 1151083 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 1.4669. Min Range: -1.4669

Max Act: 0.8110. Min Act: -0.0000

Data Index: 966887 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 1.4669. Min Range: -1.4669

Max Act: 0.8515. Min Act: -0.0000

Data Index: 353405 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 1.4669. Min Range: -1.4669

Max Act: 0.8063. Min Act: -0.0000

Data Index: 632195 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 1.4669. Min Range: -1.4669

Max Act: 0.7777. Min Act: -0.0000

Data Index: 324018 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 1.4669. Min Range: -1.4669

Max Act: 0.8423. Min Act: -0.0000

Data Index: 1501701 (Python Code)

Max Activating Token Index: 411

Text #17

Max Range: 1.4669. Min Range: -1.4669

Max Act: 0.7628. Min Act: -0.0000

Data Index: 677547 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 1.4669. Min Range: -1.4669

Max Act: 0.8235. Min Act: -0.0000

Data Index: 1358057 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 1.4669. Min Range: -1.4669

Max Act: 0.8081. Min Act: -0.0000

Data Index: 1069136 (C4 (Web Text))

Max Activating Token Index: 367