Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4912 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.5913. Min Range: -1.5913

Max Act: 1.5913. Min Act: -0.0000

Data Index: 271961 (The Pile)

Max Activating Token Index: 386

Text #1

Max Range: 1.5913. Min Range: -1.5913

Max Act: 1.3056. Min Act: -0.0000

Data Index: 396034 (The Pile)

Max Activating Token Index: 172

Text #2

Max Range: 1.5913. Min Range: -1.5913

Max Act: 1.5152. Min Act: -0.0000

Data Index: 261552 (The Pile)

Max Activating Token Index: 213

Text #3

Max Range: 1.5913. Min Range: -1.5913

Max Act: 1.5031. Min Act: -0.0000

Data Index: 1857506 (The Pile)

Max Activating Token Index: 134

Text #4

Max Range: 1.5913. Min Range: -1.5913

Max Act: 1.3400. Min Act: -0.0000

Data Index: 1174351 (The Pile)

Max Activating Token Index: 117

Text #5

Max Range: 1.5913. Min Range: -1.5913

Max Act: 1.3257. Min Act: -0.0000

Data Index: 807789 (The Pile)

Max Activating Token Index: 673

Text #6

Max Range: 1.5913. Min Range: -1.5913

Max Act: 1.3339. Min Act: -0.0000

Data Index: 383558 (The Pile)

Max Activating Token Index: 522

Text #7

Max Range: 1.5913. Min Range: -1.5913

Max Act: 1.3126. Min Act: -0.0000

Data Index: 1116784 (The Pile)

Max Activating Token Index: 956

Text #8

Max Range: 1.5913. Min Range: -1.5913

Max Act: 1.3811. Min Act: -0.0000

Data Index: 342839 (The Pile)

Max Activating Token Index: 143

Text #9

Max Range: 1.5913. Min Range: -1.5913

Max Act: 1.2822. Min Act: -0.0000

Data Index: 632580 (The Pile)

Max Activating Token Index: 386

Text #10

Max Range: 1.5913. Min Range: -1.5913

Max Act: 1.2599. Min Act: -0.0000

Data Index: 1550750 (The Pile)

Max Activating Token Index: 573

Text #11

Max Range: 1.5913. Min Range: -1.5913

Max Act: 1.3168. Min Act: -0.0000

Data Index: 677721 (The Pile)

Max Activating Token Index: 615

Text #12

Max Range: 1.5913. Min Range: -1.5913

Max Act: 1.2904. Min Act: -0.0000

Data Index: 300692 (The Pile)

Max Activating Token Index: 393

Text #13

Max Range: 1.5913. Min Range: -1.5913

Max Act: 1.2182. Min Act: -0.0000

Data Index: 410494 (The Pile)

Max Activating Token Index: 789

Text #14

Max Range: 1.5913. Min Range: -1.5913

Max Act: 1.2842. Min Act: -0.0000

Data Index: 1706261 (The Pile)

Max Activating Token Index: 176

Text #15

Max Range: 1.5913. Min Range: -1.5913

Max Act: 1.1341. Min Act: -0.0000

Data Index: 117839 (The Pile)

Max Activating Token Index: 675

Text #16

Max Range: 1.5913. Min Range: -1.5913

Max Act: 1.2378. Min Act: -0.0000

Data Index: 1880398 (The Pile)

Max Activating Token Index: 217

Text #17

Max Range: 1.5913. Min Range: -1.5913

Max Act: 1.0894. Min Act: -0.0000

Data Index: 1212489 (The Pile)

Max Activating Token Index: 717

Text #18

Max Range: 1.5913. Min Range: -1.5913

Max Act: 1.1554. Min Act: -0.0000

Data Index: 1617926 (The Pile)

Max Activating Token Index: 519

Text #19

Max Range: 1.5913. Min Range: -1.5913

Max Act: 1.1406. Min Act: -0.0000

Data Index: 416974 (The Pile)

Max Activating Token Index: 675