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

Dataset: The Pile

Neuron 3104 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.6806. Min Act: -0.0000

Data Index: 1235551 (The Pile)

Max Activating Token Index: 710

Text #1

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.6237. Min Act: -0.0000

Data Index: 457463 (The Pile)

Max Activating Token Index: 8

Text #2

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5721. Min Act: -0.0000

Data Index: 1928657 (The Pile)

Max Activating Token Index: 153

Text #3

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.6043. Min Act: -0.0000

Data Index: 132647 (The Pile)

Max Activating Token Index: 509

Text #4

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5481. Min Act: -0.0000

Data Index: 438947 (The Pile)

Max Activating Token Index: 928

Text #5

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5280. Min Act: -0.0000

Data Index: 45580 (The Pile)

Max Activating Token Index: 666

Text #6

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5276. Min Act: -0.0000

Data Index: 1695597 (The Pile)

Max Activating Token Index: 70

Text #7

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5693. Min Act: -0.0000

Data Index: 994481 (The Pile)

Max Activating Token Index: 194

Text #8

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5337. Min Act: -0.0000

Data Index: 589536 (The Pile)

Max Activating Token Index: 140

Text #9

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5360. Min Act: -0.0000

Data Index: 1865288 (The Pile)

Max Activating Token Index: 389

Text #10

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5140. Min Act: -0.0000

Data Index: 528819 (The Pile)

Max Activating Token Index: 340

Text #11

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5001. Min Act: -0.0000

Data Index: 1426645 (The Pile)

Max Activating Token Index: 268

Text #12

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5086. Min Act: -0.0000

Data Index: 1336002 (The Pile)

Max Activating Token Index: 221

Text #13

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.4796. Min Act: -0.0000

Data Index: 210677 (The Pile)

Max Activating Token Index: 693

Text #14

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.4758. Min Act: -0.0000

Data Index: 1605861 (The Pile)

Max Activating Token Index: 339

Text #15

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.4715. Min Act: -0.0000

Data Index: 445865 (The Pile)

Max Activating Token Index: 528

Text #16

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5047. Min Act: -0.0000

Data Index: 1330347 (The Pile)

Max Activating Token Index: 129

Text #17

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.4692. Min Act: -0.0000

Data Index: 1781596 (The Pile)

Max Activating Token Index: 224

Text #18

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.4920. Min Act: -0.0000

Data Index: 735211 (The Pile)

Max Activating Token Index: 155

Text #19

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.4458. Min Act: -0.0000

Data Index: 359883 (The Pile)

Max Activating Token Index: 802