Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3442 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.5694. Min Act: -0.0000

Data Index: 1999315 (The Pile)

Max Activating Token Index: 399

Text #1

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.4422. Min Act: -0.0000

Data Index: 209026 (The Pile)

Max Activating Token Index: 529

Text #2

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.4093. Min Act: 0.0000

Data Index: 969014 (The Pile)

Max Activating Token Index: 850

Text #3

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.3382. Min Act: -0.0000

Data Index: 814744 (The Pile)

Max Activating Token Index: 840

Text #4

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.3842. Min Act: -0.0000

Data Index: 682097 (The Pile)

Max Activating Token Index: 538

Text #5

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.3325. Min Act: -0.0000

Data Index: 1918428 (The Pile)

Max Activating Token Index: 544

Text #6

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.2648. Min Act: -0.0000

Data Index: 1782261 (The Pile)

Max Activating Token Index: 747

Text #7

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.2958. Min Act: -0.0000

Data Index: 28449 (The Pile)

Max Activating Token Index: 915

Text #8

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.2873. Min Act: -0.0000

Data Index: 579391 (The Pile)

Max Activating Token Index: 541

Text #9

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.2849. Min Act: -0.0000

Data Index: 1556485 (The Pile)

Max Activating Token Index: 325

Text #10

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.2390. Min Act: -0.0000

Data Index: 1963098 (The Pile)

Max Activating Token Index: 734

Text #11

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.2978. Min Act: -0.0000

Data Index: 313607 (The Pile)

Max Activating Token Index: 363

Text #12

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.2271. Min Act: -0.0000

Data Index: 941756 (The Pile)

Max Activating Token Index: 429

Text #13

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.2894. Min Act: -0.0000

Data Index: 442964 (The Pile)

Max Activating Token Index: 388

Text #14

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.2711. Min Act: -0.0000

Data Index: 536658 (The Pile)

Max Activating Token Index: 713

Text #15

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.1936. Min Act: 0.0000

Data Index: 721362 (The Pile)

Max Activating Token Index: 207

Text #16

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.1765. Min Act: -0.0000

Data Index: 1946692 (The Pile)

Max Activating Token Index: 675

Text #17

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.2490. Min Act: -0.0000

Data Index: 632386 (The Pile)

Max Activating Token Index: 323

Text #18

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.2006. Min Act: -0.0000

Data Index: 1708646 (The Pile)

Max Activating Token Index: 485

Text #19

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.2000. Min Act: -0.0000

Data Index: 1915172 (The Pile)

Max Activating Token Index: 627