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

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

Neuron 928 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: 1.5827. Min Range: -1.5827

Max Act: 1.5827. Min Act: -0.0000

Data Index: 407926 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 1.5827. Min Range: -1.5827

Max Act: 1.1558. Min Act: -0.0000

Data Index: 227391 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 1.5827. Min Range: -1.5827

Max Act: 1.0157. Min Act: -0.0000

Data Index: 63628 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 1.5827. Min Range: -1.5827

Max Act: 0.9545. Min Act: -0.0000

Data Index: 524285 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 1.5827. Min Range: -1.5827

Max Act: 0.9785. Min Act: -0.0000

Data Index: 24899 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 1.5827. Min Range: -1.5827

Max Act: 0.8750. Min Act: -0.0000

Data Index: 1441344 (Python Code)

Max Activating Token Index: 942

Text #6

Max Range: 1.5827. Min Range: -1.5827

Max Act: 0.8728. Min Act: -0.0000

Data Index: 196887 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 1.5827. Min Range: -1.5827

Max Act: 0.8303. Min Act: -0.0000

Data Index: 1011904 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 1.5827. Min Range: -1.5827

Max Act: 0.7994. Min Act: -0.0000

Data Index: 377939 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 1.5827. Min Range: -1.5827

Max Act: 0.7428. Min Act: -0.0000

Data Index: 302745 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 1.5827. Min Range: -1.5827

Max Act: 0.7959. Min Act: -0.0000

Data Index: 1223925 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 1.5827. Min Range: -1.5827

Max Act: 0.7659. Min Act: -0.0000

Data Index: 1115997 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 1.5827. Min Range: -1.5827

Max Act: 0.7585. Min Act: -0.0000

Data Index: 37144 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 1.5827. Min Range: -1.5827

Max Act: 0.7930. Min Act: -0.0000

Data Index: 812460 (C4 (Web Text))

Max Activating Token Index: 275

Text #14

Max Range: 1.5827. Min Range: -1.5827

Max Act: 0.7925. Min Act: -0.0000

Data Index: 917549 (C4 (Web Text))

Max Activating Token Index: 465

Text #15

Max Range: 1.5827. Min Range: -1.5827

Max Act: 0.7748. Min Act: -0.0000

Data Index: 293842 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 1.5827. Min Range: -1.5827

Max Act: 0.7530. Min Act: -0.0000

Data Index: 1395907 (Python Code)

Max Activating Token Index: 810

Text #17

Max Range: 1.5827. Min Range: -1.5827

Max Act: 0.7239. Min Act: -0.0000

Data Index: 1445283 (Python Code)

Max Activating Token Index: 892

Text #18

Max Range: 1.5827. Min Range: -1.5827

Max Act: 0.7356. Min Act: -0.0000

Data Index: 78036 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 1.5827. Min Range: -1.5827

Max Act: 0.7500. Min Act: -0.0000

Data Index: 1457280 (Python Code)

Max Activating Token Index: 145