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

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

Neuron 4585 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: 1.6312. Min Range: -1.6312

Max Act: 1.6312. Min Act: -0.0000

Data Index: 112181 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 1.6312. Min Range: -1.6312

Max Act: 1.5659. Min Act: -0.0000

Data Index: 1290930 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 1.6312. Min Range: -1.6312

Max Act: 1.4609. Min Act: -0.0000

Data Index: 1027346 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 1.6312. Min Range: -1.6312

Max Act: 1.5168. Min Act: -0.0000

Data Index: 197075 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 1.6312. Min Range: -1.6312

Max Act: 1.5082. Min Act: -0.0000

Data Index: 956225 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 1.6312. Min Range: -1.6312

Max Act: 1.4837. Min Act: -0.0000

Data Index: 995296 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 1.6312. Min Range: -1.6312

Max Act: 1.3021. Min Act: -0.0000

Data Index: 1088138 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 1.6312. Min Range: -1.6312

Max Act: 1.2629. Min Act: -0.0000

Data Index: 599705 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 1.6312. Min Range: -1.6312

Max Act: 1.2522. Min Act: -0.0000

Data Index: 979721 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 1.6312. Min Range: -1.6312

Max Act: 1.1789. Min Act: -0.0000

Data Index: 812476 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 1.6312. Min Range: -1.6312

Max Act: 1.2233. Min Act: -0.0000

Data Index: 537651 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 1.6312. Min Range: -1.6312

Max Act: 1.2171. Min Act: -0.0000

Data Index: 1229540 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 1.6312. Min Range: -1.6312

Max Act: 1.1444. Min Act: -0.0000

Data Index: 982713 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 1.6312. Min Range: -1.6312

Max Act: 1.2864. Min Act: -0.0000

Data Index: 953732 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 1.6312. Min Range: -1.6312

Max Act: 1.2043. Min Act: -0.0000

Data Index: 322770 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 1.6312. Min Range: -1.6312

Max Act: 1.1986. Min Act: -0.0000

Data Index: 162199 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 1.6312. Min Range: -1.6312

Max Act: 1.1806. Min Act: -0.0000

Data Index: 845930 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 1.6312. Min Range: -1.6312

Max Act: 1.2453. Min Act: -0.0000

Data Index: 580264 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 1.6312. Min Range: -1.6312

Max Act: 1.0952. Min Act: -0.0000

Data Index: 87563 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 1.6312. Min Range: -1.6312

Max Act: 1.1634. Min Act: -0.0000

Data Index: 342308 (C4 (Web Text))

Max Activating Token Index: 464