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

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

Neuron 4664 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: 1.3661. Min Range: -1.3661

Max Act: 1.3661. Min Act: -0.0000

Data Index: 978537 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 1.3661. Min Range: -1.3661

Max Act: 1.0953. Min Act: -0.0000

Data Index: 759314 (C4 (Web Text))

Max Activating Token Index: 244

Text #2

Max Range: 1.3661. Min Range: -1.3661

Max Act: 1.1289. Min Act: -0.0000

Data Index: 203789 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 1.3661. Min Range: -1.3661

Max Act: 1.0425. Min Act: -0.0000

Data Index: 494 (C4 (Web Text))

Max Activating Token Index: 559

Text #4

Max Range: 1.3661. Min Range: -1.3661

Max Act: 1.1619. Min Act: -0.0000

Data Index: 591246 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 1.3661. Min Range: -1.3661

Max Act: 1.0479. Min Act: -0.0000

Data Index: 1015994 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 1.3661. Min Range: -1.3661

Max Act: 0.9935. Min Act: -0.0000

Data Index: 459218 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 1.3661. Min Range: -1.3661

Max Act: 0.9639. Min Act: -0.0000

Data Index: 1247355 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 1.3661. Min Range: -1.3661

Max Act: 0.9537. Min Act: -0.0000

Data Index: 926334 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 1.3661. Min Range: -1.3661

Max Act: 0.9320. Min Act: -0.0000

Data Index: 106499 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 1.3661. Min Range: -1.3661

Max Act: 0.9123. Min Act: -0.0000

Data Index: 1172774 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 1.3661. Min Range: -1.3661

Max Act: 0.8760. Min Act: -0.0000

Data Index: 1256634 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 1.3661. Min Range: -1.3661

Max Act: 0.8943. Min Act: -0.0000

Data Index: 666962 (C4 (Web Text))

Max Activating Token Index: 1018

Text #13

Max Range: 1.3661. Min Range: -1.3661

Max Act: 0.8519. Min Act: -0.0000

Data Index: 204971 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 1.3661. Min Range: -1.3661

Max Act: 0.9223. Min Act: 0.0000

Data Index: 381405 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 1.3661. Min Range: -1.3661

Max Act: 0.9104. Min Act: 0.0000

Data Index: 314608 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 1.3661. Min Range: -1.3661

Max Act: 0.8949. Min Act: -0.0000

Data Index: 1110642 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 1.3661. Min Range: -1.3661

Max Act: 0.8348. Min Act: -0.0000

Data Index: 351431 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 1.3661. Min Range: -1.3661

Max Act: 0.8097. Min Act: 0.0000

Data Index: 207545 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 1.3661. Min Range: -1.3661

Max Act: 0.8352. Min Act: -0.0000

Data Index: 352367 (C4 (Web Text))

Max Activating Token Index: 220