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

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

Neuron 3563 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: 1.5454. Min Range: -1.5454

Max Act: 1.5454. Min Act: -0.0000

Data Index: 368382 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 1.5454. Min Range: -1.5454

Max Act: 1.3284. Min Act: -0.0000

Data Index: 480857 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 1.5454. Min Range: -1.5454

Max Act: 0.9777. Min Act: -0.0000

Data Index: 762506 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 1.5454. Min Range: -1.5454

Max Act: 1.0024. Min Act: -0.0000

Data Index: 541172 (C4 (Web Text))

Max Activating Token Index: 559

Text #4

Max Range: 1.5454. Min Range: -1.5454

Max Act: 0.9873. Min Act: -0.0000

Data Index: 132399 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 1.5454. Min Range: -1.5454

Max Act: 0.8519. Min Act: -0.0000

Data Index: 928828 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 1.5454. Min Range: -1.5454

Max Act: 0.9656. Min Act: -0.0000

Data Index: 273988 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 1.5454. Min Range: -1.5454

Max Act: 0.8957. Min Act: -0.0000

Data Index: 682707 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 1.5454. Min Range: -1.5454

Max Act: 0.8717. Min Act: -0.0000

Data Index: 307114 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 1.5454. Min Range: -1.5454

Max Act: 0.8597. Min Act: -0.0000

Data Index: 929214 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 1.5454. Min Range: -1.5454

Max Act: 0.9567. Min Act: -0.0000

Data Index: 115007 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 1.5454. Min Range: -1.5454

Max Act: 0.8948. Min Act: -0.0000

Data Index: 1148480 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 1.5454. Min Range: -1.5454

Max Act: 0.8844. Min Act: -0.0000

Data Index: 982976 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 1.5454. Min Range: -1.5454

Max Act: 0.8437. Min Act: -0.0000

Data Index: 569427 (C4 (Web Text))

Max Activating Token Index: 502

Text #14

Max Range: 1.5454. Min Range: -1.5454

Max Act: 0.7846. Min Act: -0.0000

Data Index: 1322691 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 1.5454. Min Range: -1.5454

Max Act: 0.7963. Min Act: -0.0000

Data Index: 1127921 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 1.5454. Min Range: -1.5454

Max Act: 0.8984. Min Act: -0.0000

Data Index: 452975 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 1.5454. Min Range: -1.5454

Max Act: 0.8163. Min Act: -0.0000

Data Index: 90985 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 1.5454. Min Range: -1.5454

Max Act: 0.7900. Min Act: -0.0000

Data Index: 975538 (C4 (Web Text))

Max Activating Token Index: 387

Text #19

Max Range: 1.5454. Min Range: -1.5454

Max Act: 0.8307. Min Act: -0.0000

Data Index: 357557 (C4 (Web Text))

Max Activating Token Index: 105