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

Dataset: The Pile

Neuron 1146 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1682. Min Act: -0.0000

Data Index: 624989 (The Pile)

Max Activating Token Index: 906

Text #1

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1723. Min Act: -0.0000

Data Index: 357742 (The Pile)

Max Activating Token Index: 341

Text #2

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1549. Min Act: -0.0000

Data Index: 1545785 (The Pile)

Max Activating Token Index: 574

Text #3

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1538. Min Act: -0.0000

Data Index: 379891 (The Pile)

Max Activating Token Index: 361

Text #4

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1414. Min Act: -0.0000

Data Index: 787127 (The Pile)

Max Activating Token Index: 989

Text #5

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1516. Min Act: -0.0000

Data Index: 975089 (The Pile)

Max Activating Token Index: 507

Text #6

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1378. Min Act: -0.0000

Data Index: 1752954 (The Pile)

Max Activating Token Index: 1017

Text #7

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1643. Min Act: -0.0000

Data Index: 47267 (The Pile)

Max Activating Token Index: 360

Text #8

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1484. Min Act: -0.0000

Data Index: 1419917 (The Pile)

Max Activating Token Index: 335

Text #9

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1353. Min Act: 0.0000

Data Index: 1106647 (The Pile)

Max Activating Token Index: 528

Text #10

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1201. Min Act: -0.0000

Data Index: 1430053 (The Pile)

Max Activating Token Index: 843

Text #11

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1280. Min Act: -0.0000

Data Index: 1678260 (The Pile)

Max Activating Token Index: 923

Text #12

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1488. Min Act: -0.0000

Data Index: 482985 (The Pile)

Max Activating Token Index: 821

Text #13

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1371. Min Act: -0.0000

Data Index: 1812763 (The Pile)

Max Activating Token Index: 143

Text #14

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1386. Min Act: -0.0000

Data Index: 445516 (The Pile)

Max Activating Token Index: 744

Text #15

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1360. Min Act: -0.0000

Data Index: 156140 (The Pile)

Max Activating Token Index: 498

Text #16

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1442. Min Act: -0.0000

Data Index: 1301489 (The Pile)

Max Activating Token Index: 538

Text #17

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1605. Min Act: -0.0000

Data Index: 650442 (The Pile)

Max Activating Token Index: 203

Text #18

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1331. Min Act: -0.0000

Data Index: 318300 (The Pile)

Max Activating Token Index: 465

Text #19

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1276. Min Act: -0.0000

Data Index: 1921291 (The Pile)

Max Activating Token Index: 994