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

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

Neuron 3590 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: 1.9099. Min Range: -1.9099

Max Act: 1.9099. Min Act: -0.0000

Data Index: 92064 (C4 (Web Text))

Max Activating Token Index: 304

Text #1

Max Range: 1.9099. Min Range: -1.9099

Max Act: 1.5500. Min Act: -0.0000

Data Index: 423665 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 1.9099. Min Range: -1.9099

Max Act: 1.3609. Min Act: -0.0000

Data Index: 384570 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 1.9099. Min Range: -1.9099

Max Act: 1.3274. Min Act: -0.0000

Data Index: 1078532 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 1.9099. Min Range: -1.9099

Max Act: 1.2173. Min Act: -0.0000

Data Index: 918293 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 1.9099. Min Range: -1.9099

Max Act: 1.0072. Min Act: -0.0000

Data Index: 1301301 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 1.9099. Min Range: -1.9099

Max Act: 1.0493. Min Act: -0.0000

Data Index: 1145958 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 1.9099. Min Range: -1.9099

Max Act: 1.1095. Min Act: -0.0000

Data Index: 879500 (C4 (Web Text))

Max Activating Token Index: 459

Text #8

Max Range: 1.9099. Min Range: -1.9099

Max Act: 1.0967. Min Act: -0.0000

Data Index: 599932 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 1.9099. Min Range: -1.9099

Max Act: 1.0886. Min Act: -0.0000

Data Index: 298345 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 1.9099. Min Range: -1.9099

Max Act: 1.0688. Min Act: -0.0000

Data Index: 486363 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 1.9099. Min Range: -1.9099

Max Act: 1.0573. Min Act: -0.0000

Data Index: 242107 (C4 (Web Text))

Max Activating Token Index: 376

Text #12

Max Range: 1.9099. Min Range: -1.9099

Max Act: 1.0904. Min Act: -0.0000

Data Index: 116259 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 1.9099. Min Range: -1.9099

Max Act: 0.9736. Min Act: -0.0000

Data Index: 418092 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 1.9099. Min Range: -1.9099

Max Act: 1.0700. Min Act: -0.0000

Data Index: 383110 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 1.9099. Min Range: -1.9099

Max Act: 1.0410. Min Act: -0.0000

Data Index: 904646 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 1.9099. Min Range: -1.9099

Max Act: 0.9739. Min Act: -0.0000

Data Index: 327955 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 1.9099. Min Range: -1.9099

Max Act: 1.0500. Min Act: -0.0000

Data Index: 561768 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 1.9099. Min Range: -1.9099

Max Act: 1.1016. Min Act: -0.0000

Data Index: 924990 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 1.9099. Min Range: -1.9099

Max Act: 0.9617. Min Act: -0.0000

Data Index: 2007 (C4 (Web Text))

Max Activating Token Index: 782